diff --git a/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md b/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md index 5e1eda99..5fcd1158 100644 --- a/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md +++ b/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md @@ -1,4 +1,4 @@ -# Results for ghcr.io/docling-project/docling-serve as of 2026-11-09T04:51:56.431368122Z +# Results for ghcr.io/docling-project/docling-serve as of 2026-11-16T04:49:29.128279992Z Here are the results: @@ -91,128 +91,128 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:51:40 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:40 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:51:40 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:51:40 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:51:40 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:51:40 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:51:40 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:51:40 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:51:40 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:51:40 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:51:40 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:51:40 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:51:40 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:51:40 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/ready$,/health$,/livez$,/healthz$,/readyz$) -INFO: 04:51:40 - uvicorn.error - Started server process [1] -INFO: 04:51:40 - uvicorn.error - Waiting for application startup. -INFO: 04:51:40 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:41 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:51:41 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:41 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:51:41 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:51:42 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 19ad2e40917b3482b19a071b877d5fef -INFO: 04:51:42 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:51:42 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:51:42 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:51:42.197850242 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:51:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:51:42 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:51:42 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:51:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:51:45 - docling.document_converter - Going to convert document batch... -INFO: 04:51:45 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 0866b38c0a68478c38298a7b37389e4e -INFO: 04:51:45 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:51:45 - docling.document_converter - Finished converting document file in 0.63 sec. +INFO: 04:48:58 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:48:58 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:48:58 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:48:58 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:48:58 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:48:58 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:48:58 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:48:58 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:48:58 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:48:58 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:48:58 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:48:58 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:48:58 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:48:58 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/healthz$,/readyz$,/ready$,/metrics$,/livez$) +INFO: 04:48:59 - uvicorn.error - Started server process [1] +INFO: 04:48:59 - uvicorn.error - Waiting for application startup. +INFO: 04:48:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:49:00 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:49:00 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:49:00 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:49:00 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:49:00 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 097e758d3c7b58f3f29eac6fe2f25c0d +INFO: 04:49:00 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:49:00 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:49:00 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:49:00.424341463 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:49:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:49:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:49:00 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:49:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:49:04 - docling.document_converter - Going to convert document batch... +INFO: 04:49:04 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 3816c1a2f2beaf0c2f8e763af5d184d4 +INFO: 04:49:04 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:49:04 - docling.document_converter - Finished converting document file in 0.67 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:51:45 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. -INFO: 04:51:45 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 45d77d54-50d8-4612-ac07-cfade607d5e1 in 0.70 seconds -INFO: 04:51:45 - uvicorn.access - 172.17.0.1:48534 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:51:45 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:51:45 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:51:45 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:51:45 - docling_serve.app - [TENANT_ID] Task 6973abbd-cc40-4739-b869-355798bfb2bf created with tenant_id='default' -INFO: 04:51:45 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 6973abbd-cc40-4739-b869-355798bfb2bf -INFO: 04:51:45 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:51:46 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 0866b38c0a68478c38298a7b37389e4e -INFO: 04:51:46 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:51:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:51:46 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:51:46 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:51:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:51:47 - docling.document_converter - Going to convert document batch... -INFO: 04:51:47 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 0866b38c0a68478c38298a7b37389e4e -INFO: 04:51:47 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:51:47 - docling.document_converter - Finished converting document file in 0.46 sec. +INFO: 04:49:04 - docling_jobkit.convert.results - Processed 1 docs in 0.78 seconds. +INFO: 04:49:04 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 6613bf0e-ea5e-4f31-8208-36bcafb720f1 in 0.78 seconds +INFO: 04:49:04 - uvicorn.access - 172.17.0.1:51720 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:49:04 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:49:04 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:49:04 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:49:04 - docling_serve.app - [TENANT_ID] Task af438df8-9995-4251-a849-7a64c01a8464 created with tenant_id='default' +INFO: 04:49:04 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task af438df8-9995-4251-a849-7a64c01a8464 +INFO: 04:49:04 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:49:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3816c1a2f2beaf0c2f8e763af5d184d4 +INFO: 04:49:05 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:49:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:49:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:49:05 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:49:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:49:06 - docling.document_converter - Going to convert document batch... +INFO: 04:49:06 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 3816c1a2f2beaf0c2f8e763af5d184d4 +INFO: 04:49:06 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:49:06 - docling.document_converter - Finished converting document file in 0.33 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:51:47 - docling_jobkit.convert.results - Processed 1 docs in 0.47 seconds. -INFO: 04:51:47 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 6973abbd-cc40-4739-b869-355798bfb2bf in 0.47 seconds -INFO: 04:51:47 - uvicorn.access - 172.17.0.1:48534 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:51:47 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:51:47 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:51:47 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:51:47 - docling_serve.app - [TENANT_ID] Task 2b028be8-4cd1-4f4a-a740-be9a68fccc8a created with tenant_id='default' -INFO: 04:51:47 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 2b028be8-4cd1-4f4a-a740-be9a68fccc8a -INFO: 04:51:47 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:51:48 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash ce20ab6b69883db8aa2a825d6c907b4f -INFO: 04:51:48 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:51:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:51:48 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:51:48 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:51:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:51:49 - docling.document_converter - Going to convert document batch... -INFO: 04:51:49 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash ce20ab6b69883db8aa2a825d6c907b4f -INFO: 04:51:49 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:51:49 - docling.document_converter - Finished converting document file in 0.47 sec. +INFO: 04:49:06 - docling_jobkit.convert.results - Processed 1 docs in 0.33 seconds. +INFO: 04:49:06 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job af438df8-9995-4251-a849-7a64c01a8464 in 0.33 seconds +INFO: 04:49:06 - uvicorn.access - 172.17.0.1:51720 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:49:06 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:49:06 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:49:06 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:49:06 - docling_serve.app - [TENANT_ID] Task 3f1f841f-e307-4bef-a23b-94b1f2bbc24c created with tenant_id='default' +INFO: 04:49:06 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 3f1f841f-e307-4bef-a23b-94b1f2bbc24c +INFO: 04:49:06 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:49:07 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 24a1929d0509453d5da5768e3aa68fa7 +INFO: 04:49:07 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:49:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:49:07 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:49:07 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:49:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:49:07 - docling.document_converter - Going to convert document batch... +INFO: 04:49:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 24a1929d0509453d5da5768e3aa68fa7 +INFO: 04:49:07 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:49:07 - docling.document_converter - Finished converting document file in 0.24 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:51:49 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:51:49 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2b028be8-4cd1-4f4a-a740-be9a68fccc8a in 0.50 seconds -INFO: 04:51:49 - uvicorn.access - 172.17.0.1:48534 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:51:50 - uvicorn.access - 172.17.0.1:48534 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:51:50 - uvicorn.access - 172.17.0.1:48534 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:49:07 - docling_jobkit.convert.results - Processed 1 docs in 0.28 seconds. +INFO: 04:49:07 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 3f1f841f-e307-4bef-a23b-94b1f2bbc24c in 0.28 seconds +INFO: 04:49:08 - uvicorn.access - 172.17.0.1:51720 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:49:09 - uvicorn.access - 172.17.0.1:51720 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:49:09 - uvicorn.access - 172.17.0.1:51720 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -250,128 +250,128 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:50:31 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:50:31 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:50:31 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:50:32 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:50:32 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:50:32 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:50:32 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:50:32 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:50:32 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:50:32 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:50:32 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:50:32 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:50:32 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:50:32 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/ready$,/healthz$,/livez$,/health$,/readyz$) -INFO: 04:50:32 - uvicorn.error - Started server process [1] -INFO: 04:50:32 - uvicorn.error - Waiting for application startup. -INFO: 04:50:32 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:50:33 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:50:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:50:33 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:50:33 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:50:34 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 21a5bdafbfbe81af0bbfe0fd7eed352d -INFO: 04:50:34 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:50:34 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:50:34 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:50:34.082248999 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:50:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:50:34 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:50:34 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:50:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:50:39 - docling.document_converter - Going to convert document batch... -INFO: 04:50:39 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash f1eabb3ad36ee70cf220c6899a7dd87c -INFO: 04:50:39 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:50:39 - docling.document_converter - Finished converting document file in 0.94 sec. +INFO: 04:48:52 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:48:52 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:48:52 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:48:53 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:48:53 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:48:53 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:48:53 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:48:53 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:48:53 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:48:53 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:48:53 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:48:53 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:48:53 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:48:53 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/ready$,/healthz$,/readyz$,/metrics$,/health$) +INFO: 04:48:53 - uvicorn.error - Started server process [1] +INFO: 04:48:53 - uvicorn.error - Waiting for application startup. +INFO: 04:48:53 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:48:54 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:48:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:48:54 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:48:54 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:48:54 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c8b041d85ac6d909a956e64bb3efea22 +INFO: 04:48:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:48:54 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:48:54 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:48:54.784620024 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:48:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:48:55 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:48:55 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:48:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:48:57 - docling.document_converter - Going to convert document batch... +INFO: 04:48:57 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash eda35f6b48554f302dc3a46b4d143bd8 +INFO: 04:48:57 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:48:58 - docling.document_converter - Finished converting document file in 0.49 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:50:39 - docling_jobkit.convert.results - Processed 1 docs in 1.15 seconds. -INFO: 04:50:39 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 0dfeb6b6-e8b0-4bf0-97f4-2f8c3454fbe4 in 1.15 seconds -INFO: 04:50:40 - uvicorn.access - 172.17.0.1:45898 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:50:40 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:50:40 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:50:40 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:50:40 - docling_serve.app - [TENANT_ID] Task 1a9b8623-16f0-4d48-8396-01bf6f3e04d2 created with tenant_id='default' -INFO: 04:50:40 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 1a9b8623-16f0-4d48-8396-01bf6f3e04d2 -INFO: 04:50:40 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:50:41 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f1eabb3ad36ee70cf220c6899a7dd87c -INFO: 04:50:41 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:50:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:50:41 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:50:41 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:50:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:50:43 - docling.document_converter - Going to convert document batch... -INFO: 04:50:43 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash f1eabb3ad36ee70cf220c6899a7dd87c -INFO: 04:50:43 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:50:43 - docling.document_converter - Finished converting document file in 0.55 sec. +INFO: 04:48:58 - docling_jobkit.convert.results - Processed 1 docs in 0.73 seconds. +INFO: 04:48:58 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 90429f2c-bd90-4562-8598-91a58327be9d in 0.73 seconds +INFO: 04:48:58 - uvicorn.access - 172.17.0.1:49256 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:48:58 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:48:58 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:48:58 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:48:58 - docling_serve.app - [TENANT_ID] Task 493ae20d-05ff-4f3b-bc26-4850638725ca created with tenant_id='default' +INFO: 04:48:58 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 493ae20d-05ff-4f3b-bc26-4850638725ca +INFO: 04:48:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:48:59 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash eda35f6b48554f302dc3a46b4d143bd8 +INFO: 04:48:59 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:48:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:48:59 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:48:59 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:48:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:49:00 - docling.document_converter - Going to convert document batch... +INFO: 04:49:00 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash eda35f6b48554f302dc3a46b4d143bd8 +INFO: 04:49:00 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:49:00 - docling.document_converter - Finished converting document file in 0.35 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:50:43 - docling_jobkit.convert.results - Processed 1 docs in 0.55 seconds. -INFO: 04:50:43 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 1a9b8623-16f0-4d48-8396-01bf6f3e04d2 in 0.55 seconds -INFO: 04:50:44 - uvicorn.access - 172.17.0.1:45898 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:50:44 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:50:44 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:50:44 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:50:44 - docling_serve.app - [TENANT_ID] Task ae62068b-701b-4cd7-b229-34ab9d69853c created with tenant_id='default' -INFO: 04:50:44 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ae62068b-701b-4cd7-b229-34ab9d69853c -INFO: 04:50:44 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:50:45 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5067e95ed2289c3bee5a18f6b22fca49 -INFO: 04:50:45 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:50:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:50:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:50:45 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:50:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:50:46 - docling.document_converter - Going to convert document batch... -INFO: 04:50:46 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5067e95ed2289c3bee5a18f6b22fca49 -INFO: 04:50:46 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:50:46 - docling.document_converter - Finished converting document file in 0.53 sec. +INFO: 04:49:00 - docling_jobkit.convert.results - Processed 1 docs in 0.35 seconds. +INFO: 04:49:00 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 493ae20d-05ff-4f3b-bc26-4850638725ca in 0.35 seconds +INFO: 04:49:00 - uvicorn.access - 172.17.0.1:49256 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:49:00 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:49:00 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:49:00 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:49:00 - docling_serve.app - [TENANT_ID] Task afcdf2d3-5537-4ff6-acb7-f3a14f4ad894 created with tenant_id='default' +INFO: 04:49:00 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task afcdf2d3-5537-4ff6-acb7-f3a14f4ad894 +INFO: 04:49:00 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:49:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 162f4c37dd48c6a4ac03df591c289c9d +INFO: 04:49:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:49:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:49:01 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:49:01 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:49:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:49:02 - docling.document_converter - Going to convert document batch... +INFO: 04:49:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 162f4c37dd48c6a4ac03df591c289c9d +INFO: 04:49:02 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:49:02 - docling.document_converter - Finished converting document file in 0.35 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:50:46 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. -INFO: 04:50:46 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ae62068b-701b-4cd7-b229-34ab9d69853c in 0.58 seconds -INFO: 04:50:46 - uvicorn.access - 172.17.0.1:45898 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:50:47 - uvicorn.access - 172.17.0.1:45898 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:50:47 - uvicorn.access - 172.17.0.1:45898 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:49:02 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 04:49:02 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job afcdf2d3-5537-4ff6-acb7-f3a14f4ad894 in 0.38 seconds +INFO: 04:49:02 - uvicorn.access - 172.17.0.1:49256 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:49:03 - uvicorn.access - 172.17.0.1:49256 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:49:03 - uvicorn.access - 172.17.0.1:49256 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -409,128 +409,128 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:48:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:48:49 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:48:49 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:48:50 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:48:50 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:48:50 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:48:50 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:48:50 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:48:50 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:48:50 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:48:50 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:48:50 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:48:50 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:48:50 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/health$,/healthz$,/livez$,/metrics$,/readyz$) -INFO: 04:48:50 - uvicorn.error - Started server process [1] -INFO: 04:48:50 - uvicorn.error - Waiting for application startup. -INFO: 04:48:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:48:51 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:48:51 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:48:51 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:48:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:48:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b512667ec4c5e21562cdbbb72033e88f -INFO: 04:48:51 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:48:51 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:48:51 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:48:51.372784405 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:48:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:48:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:48:51 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:48:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:48:54 - docling.document_converter - Going to convert document batch... -INFO: 04:48:54 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash b09292c77e315ac85fcb9443035d8c11 -INFO: 04:48:54 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:48:55 - docling.document_converter - Finished converting document file in 0.88 sec. +INFO: 04:45:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:50 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:45:50 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:45:51 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:45:51 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:45:51 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:45:51 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:45:51 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:45:51 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:45:51 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:45:51 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:45:51 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:45:51 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:45:51 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/metrics$,/health$,/healthz$,/readyz$,/livez$) +INFO: 04:45:51 - uvicorn.error - Started server process [1] +INFO: 04:45:51 - uvicorn.error - Waiting for application startup. +INFO: 04:45:51 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:51 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:45:51 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:51 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:45:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:45:52 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b62762cda5bfbb4775f16d8561a0d4ea +INFO: 04:45:52 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:52 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:45:52 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:45:52.355777498 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:45:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:45:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:45:52 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:45:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:45:55 - docling.document_converter - Going to convert document batch... +INFO: 04:45:55 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5fdd2732f0a5c582117308ba8da9dfcd +INFO: 04:45:55 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:45:55 - docling.document_converter - Finished converting document file in 0.49 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:48:55 - docling_jobkit.convert.results - Processed 1 docs in 0.95 seconds. -INFO: 04:48:55 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 905a815c-8962-41c1-a4a6-ce5c02d7a26b in 0.95 seconds -INFO: 04:48:55 - uvicorn.access - 172.17.0.1:52338 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:48:55 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:48:55 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:48:55 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:48:55 - docling_serve.app - [TENANT_ID] Task 3899e607-ab64-4121-a611-afea1958f1f0 created with tenant_id='default' -INFO: 04:48:55 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 3899e607-ab64-4121-a611-afea1958f1f0 -INFO: 04:48:55 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:48:55 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b09292c77e315ac85fcb9443035d8c11 -INFO: 04:48:55 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:48:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:48:55 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:48:55 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:48:55 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:48:56 - docling.document_converter - Going to convert document batch... -INFO: 04:48:56 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash b09292c77e315ac85fcb9443035d8c11 -INFO: 04:48:56 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:48:57 - docling.document_converter - Finished converting document file in 0.48 sec. +INFO: 04:45:55 - docling_jobkit.convert.results - Processed 1 docs in 0.56 seconds. +INFO: 04:45:55 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 389c8bf3-b568-4666-8f07-5a0c5d5e7a30 in 0.56 seconds +INFO: 04:45:56 - uvicorn.access - 172.17.0.1:56346 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:45:56 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:45:56 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:45:56 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:45:56 - docling_serve.app - [TENANT_ID] Task c5fb0fcc-15f2-4343-aef3-37323f3bf428 created with tenant_id='default' +INFO: 04:45:56 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task c5fb0fcc-15f2-4343-aef3-37323f3bf428 +INFO: 04:45:56 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:45:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5fdd2732f0a5c582117308ba8da9dfcd +INFO: 04:45:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:45:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:45:56 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:45:56 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:45:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:45:57 - docling.document_converter - Going to convert document batch... +INFO: 04:45:57 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5fdd2732f0a5c582117308ba8da9dfcd +INFO: 04:45:57 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:45:58 - docling.document_converter - Finished converting document file in 0.46 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:48:57 - docling_jobkit.convert.results - Processed 1 docs in 0.48 seconds. -INFO: 04:48:57 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 3899e607-ab64-4121-a611-afea1958f1f0 in 0.48 seconds -INFO: 04:48:57 - uvicorn.access - 172.17.0.1:52338 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:48:57 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:48:57 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:48:57 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:48:57 - docling_serve.app - [TENANT_ID] Task c0136afd-16de-47ce-a827-7869508a888e created with tenant_id='default' -INFO: 04:48:57 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task c0136afd-16de-47ce-a827-7869508a888e -INFO: 04:48:57 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:48:57 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 46a227378a399f8172808571bb22e5ae -INFO: 04:48:57 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:48:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:48:57 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:48:57 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:48:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:48:58 - docling.document_converter - Going to convert document batch... -INFO: 04:48:58 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 46a227378a399f8172808571bb22e5ae -INFO: 04:48:58 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:48:58 - docling.document_converter - Finished converting document file in 0.47 sec. +INFO: 04:45:58 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 04:45:58 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job c5fb0fcc-15f2-4343-aef3-37323f3bf428 in 0.46 seconds +INFO: 04:45:58 - uvicorn.access - 172.17.0.1:56346 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:45:58 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:45:58 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:45:58 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:45:58 - docling_serve.app - [TENANT_ID] Task ee5e6a5f-1d67-408e-a637-ac23917ad6cb created with tenant_id='default' +INFO: 04:45:58 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ee5e6a5f-1d67-408e-a637-ac23917ad6cb +INFO: 04:45:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:45:58 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash eb63520e6f5e245277a72907049b0591 +INFO: 04:45:58 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:45:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:45:58 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:45:58 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:45:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:45:59 - docling.document_converter - Going to convert document batch... +INFO: 04:45:59 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash eb63520e6f5e245277a72907049b0591 +INFO: 04:45:59 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:45:59 - docling.document_converter - Finished converting document file in 0.34 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:743: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:48:58 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:48:58 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c0136afd-16de-47ce-a827-7869508a888e in 0.51 seconds -INFO: 04:48:59 - uvicorn.access - 172.17.0.1:52338 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:48:59 - uvicorn.access - 172.17.0.1:52338 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:48:59 - uvicorn.access - 172.17.0.1:52338 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:45:59 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:45:59 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ee5e6a5f-1d67-408e-a637-ac23917ad6cb in 0.37 seconds +INFO: 04:46:00 - uvicorn.access - 172.17.0.1:56346 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:46:00 - uvicorn.access - 172.17.0.1:56346 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:46:00 - uvicorn.access - 172.17.0.1:56346 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -568,128 +568,128 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:47:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:05 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:47:05 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:47:06 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:47:06 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:47:06 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:47:06 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:47:06 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:47:06 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:47:06 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:47:06 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:47:06 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:47:06 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:47:06 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/livez$,/readyz$,/health$,/ready$,/metrics$) -INFO: 04:47:06 - uvicorn.error - Started server process [1] -INFO: 04:47:06 - uvicorn.error - Waiting for application startup. -INFO: 04:47:09 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:09 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:47:09 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:09 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:47:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:47:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 13c598601c41ded5d7352ff5a62b3ab2 -INFO: 04:47:09 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:47:09 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:47:09 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:47:09.643039860 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:47:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:47:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:47:10 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:47:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:47:13 - docling.document_converter - Going to convert document batch... -INFO: 04:47:13 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash fb695660caba7567d48581c152baa168 -INFO: 04:47:13 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:47:13 - docling.document_converter - Finished converting document file in 0.50 sec. +INFO: 04:45:40 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:40 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:45:40 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:45:41 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:45:41 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:45:41 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:45:41 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:45:41 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:45:41 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:45:41 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:45:41 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:45:41 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:45:41 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:45:41 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/ready$,/healthz$,/health$,/metrics$,/livez$) +INFO: 04:45:41 - uvicorn.error - Started server process [1] +INFO: 04:45:41 - uvicorn.error - Waiting for application startup. +INFO: 04:45:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:46 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:45:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:46 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:45:46 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:45:46 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash dc0857f47eb37edd3a0e0e4f2dc83713 +INFO: 04:45:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:45:46 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:45:46 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:45:46.517645621 [W:onnxruntime:Default, device_discovery.cc:95 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:45:47 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:45:47 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:45:47 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:45:47 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:45:49 - docling.document_converter - Going to convert document batch... +INFO: 04:45:49 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash e7b5a9bd3e84a3dc4f325f5a3d9cd5c0 +INFO: 04:45:49 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:45:49 - docling.document_converter - Finished converting document file in 0.48 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:681: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:47:13 - docling_jobkit.convert.results - Processed 1 docs in 0.59 seconds. -INFO: 04:47:13 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4bcadc6b-24c3-4a5b-a043-eab72395ca0e in 0.59 seconds -INFO: 04:47:13 - uvicorn.access - 172.17.0.1:39620 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:47:13 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:47:13 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:47:13 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:47:13 - docling_serve.app - [TENANT_ID] Task 1b1003e4-d84b-44a8-b607-abb85964c204 created with tenant_id='default' -INFO: 04:47:13 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 1b1003e4-d84b-44a8-b607-abb85964c204 -INFO: 04:47:13 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:47:14 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb695660caba7567d48581c152baa168 -INFO: 04:47:14 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:47:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:47:14 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:47:14 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:47:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:47:15 - docling.document_converter - Going to convert document batch... -INFO: 04:47:15 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash fb695660caba7567d48581c152baa168 -INFO: 04:47:15 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:47:15 - docling.document_converter - Finished converting document file in 0.33 sec. +INFO: 04:45:49 - docling_jobkit.convert.results - Processed 1 docs in 0.54 seconds. +INFO: 04:45:49 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e5e0e8f5-0c1b-4371-8159-7d2d5626e3ab in 0.54 seconds +INFO: 04:45:50 - uvicorn.access - 172.17.0.1:46610 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:45:50 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:45:50 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:45:50 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:45:50 - docling_serve.app - [TENANT_ID] Task 80c4832d-09cf-42d9-9a51-64fbd8939402 created with tenant_id='default' +INFO: 04:45:50 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 80c4832d-09cf-42d9-9a51-64fbd8939402 +INFO: 04:45:50 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:45:50 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e7b5a9bd3e84a3dc4f325f5a3d9cd5c0 +INFO: 04:45:50 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:45:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:45:50 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:45:50 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:45:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:45:51 - docling.document_converter - Going to convert document batch... +INFO: 04:45:51 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash e7b5a9bd3e84a3dc4f325f5a3d9cd5c0 +INFO: 04:45:51 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:45:51 - docling.document_converter - Finished converting document file in 0.56 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:681: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:47:15 - docling_jobkit.convert.results - Processed 1 docs in 0.33 seconds. -INFO: 04:47:15 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 1b1003e4-d84b-44a8-b607-abb85964c204 in 0.33 seconds -INFO: 04:47:16 - uvicorn.access - 172.17.0.1:39620 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:47:16 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:47:16 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:47:16 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:47:16 - docling_serve.app - [TENANT_ID] Task 553499a6-3ff4-48d7-befc-f7245f3ffbb2 created with tenant_id='default' -INFO: 04:47:16 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 553499a6-3ff4-48d7-befc-f7245f3ffbb2 -INFO: 04:47:16 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:47:16 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 327be8a15fe7e1d23c1c5c974e2d6204 -INFO: 04:47:16 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:47:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -INFO: 04:47:16 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:47:16 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:47:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:47:17 - docling.document_converter - Going to convert document batch... -INFO: 04:47:17 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 327be8a15fe7e1d23c1c5c974e2d6204 -INFO: 04:47:17 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:47:17 - docling.document_converter - Finished converting document file in 0.46 sec. +INFO: 04:45:51 - docling_jobkit.convert.results - Processed 1 docs in 0.56 seconds. +INFO: 04:45:51 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 80c4832d-09cf-42d9-9a51-64fbd8939402 in 0.56 seconds +INFO: 04:45:52 - uvicorn.access - 172.17.0.1:46610 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:45:52 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:45:52 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:45:52 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:45:52 - docling_serve.app - [TENANT_ID] Task e9b1cbe5-c4b7-4e7d-8632-a7a67ce8bd18 created with tenant_id='default' +INFO: 04:45:52 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e9b1cbe5-c4b7-4e7d-8632-a7a67ce8bd18 +INFO: 04:45:52 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:45:52 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5446a2275395f39fdc1ad4b2e232c3a8 +INFO: 04:45:52 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:45:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:45:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:45:52 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:45:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:45:53 - docling.document_converter - Going to convert document batch... +INFO: 04:45:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5446a2275395f39fdc1ad4b2e232c3a8 +INFO: 04:45:53 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:45:54 - docling.document_converter - Finished converting document file in 0.43 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:681: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:47:17 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:47:17 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 553499a6-3ff4-48d7-befc-f7245f3ffbb2 in 0.50 seconds -INFO: 04:47:18 - uvicorn.access - 172.17.0.1:39620 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:47:18 - uvicorn.access - 172.17.0.1:39620 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:47:18 - uvicorn.access - 172.17.0.1:39620 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:45:54 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. +INFO: 04:45:54 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e9b1cbe5-c4b7-4e7d-8632-a7a67ce8bd18 in 0.45 seconds +INFO: 04:45:54 - uvicorn.access - 172.17.0.1:46610 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:45:54 - uvicorn.access - 172.17.0.1:46610 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:45:54 - uvicorn.access - 172.17.0.1:46610 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -727,152 +727,152 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:45:29 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:29 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:45:29 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:45:30 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:45:30 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:45:30 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:45:30 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:45:30 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:45:30 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:45:30 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:45:30 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:45:30 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:45:30 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:45:30 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/health$,/ready$,/metrics$,/healthz$,/livez$) -INFO: 04:45:30 - uvicorn.error - Started server process [1] -INFO: 04:45:30 - uvicorn.error - Waiting for application startup. -INFO: 04:45:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:33 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:45:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:33 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:45:33 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:45:33 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 09ad7eb42b1b02c6f33727a896018794 -INFO: 04:45:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:45:33 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:45:33 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:45:33.669428610 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:45:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:45:33,879 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:33,880 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:45:33,934 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:33,934 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:45:33,974 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:33,974 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:45:34 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:45:34 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:45:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:45:37 - docling.document_converter - Going to convert document batch... -INFO: 04:45:37 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 85169e511be645c0b5bc193fea12b6c5 -INFO: 04:45:37 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:45:37 - docling.document_converter - Finished converting document file in 0.62 sec. +INFO: 04:42:08 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:42:08 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:42:08 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:42:09 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:42:09 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:42:09 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:42:09 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:42:09 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:42:09 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:42:09 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:42:09 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:42:09 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:42:09 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:42:09 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/health$,/readyz$,/healthz$,/ready$,/metrics$) +INFO: 04:42:09 - uvicorn.error - Started server process [1] +INFO: 04:42:09 - uvicorn.error - Waiting for application startup. +INFO: 04:42:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:42:12 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:42:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:42:12 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:42:12 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:42:12 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6be9b317f4056d9fcd79255cd15cd80a +INFO: 04:42:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:42:12 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:42:12 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:42:13.060029229 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:42:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:42:13,293 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:13,295 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:42:13,394 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:13,394 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:42:13,425 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:13,425 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:42:13 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:42:13 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:42:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:42:16 - docling.document_converter - Going to convert document batch... +INFO: 04:42:16 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5db2ef6642f253aece6fe19e7b32ab0f +INFO: 04:42:16 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:42:16 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:675: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:45:37 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. -INFO: 04:45:37 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 99d2751b-246d-4909-a5a7-a8358574803f in 0.70 seconds -INFO: 04:45:37 - uvicorn.access - 172.17.0.1:57624 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:45:37 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:45:37 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:45:37 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:45:37 - docling_serve.app - [TENANT_ID] Task 7352423d-caf7-47c8-ad98-ec823e884da2 created with tenant_id='default' -INFO: 04:45:37 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 7352423d-caf7-47c8-ad98-ec823e884da2 -INFO: 04:45:37 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:45:37 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 85169e511be645c0b5bc193fea12b6c5 -INFO: 04:45:37 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:45:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:45:37,708 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:37,708 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:45:37,778 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:37,778 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:45:37,820 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:37,821 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:45:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:45:37 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:45:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:45:39 - docling.document_converter - Going to convert document batch... -INFO: 04:45:39 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 85169e511be645c0b5bc193fea12b6c5 -INFO: 04:45:39 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:45:39 - docling.document_converter - Finished converting document file in 0.70 sec. +INFO: 04:42:16 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 04:42:16 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 495addeb-cb5d-4e50-8906-35b53f1bfce3 in 0.43 seconds +INFO: 04:42:17 - uvicorn.access - 172.17.0.1:60724 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:42:17 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:42:17 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:42:17 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:42:17 - docling_serve.app - [TENANT_ID] Task 70ec8758-5f88-4bf5-ab5f-c71b6a4a2741 created with tenant_id='default' +INFO: 04:42:17 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 70ec8758-5f88-4bf5-ab5f-c71b6a4a2741 +INFO: 04:42:17 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:42:17 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5db2ef6642f253aece6fe19e7b32ab0f +INFO: 04:42:17 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:42:17 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:42:17,352 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:17,353 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:42:17,394 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:17,394 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:42:17,428 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:17,428 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:42:17 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:42:17 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:42:17 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:42:18 - docling.document_converter - Going to convert document batch... +INFO: 04:42:18 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5db2ef6642f253aece6fe19e7b32ab0f +INFO: 04:42:18 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:42:18 - docling.document_converter - Finished converting document file in 0.35 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:675: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:45:39 - docling_jobkit.convert.results - Processed 1 docs in 0.71 seconds. -INFO: 04:45:39 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 7352423d-caf7-47c8-ad98-ec823e884da2 in 0.71 seconds -INFO: 04:45:39 - uvicorn.access - 172.17.0.1:57624 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:45:39 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:45:39 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:45:39 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:45:39 - docling_serve.app - [TENANT_ID] Task 92343079-3be5-40e2-972b-a23b6e6d4deb created with tenant_id='default' -INFO: 04:45:39 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 92343079-3be5-40e2-972b-a23b6e6d4deb -INFO: 04:45:39 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:45:39 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 44834b4eb26b8d8aa7ba8a2194d47d80 -INFO: 04:45:39 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:45:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:45:39,737 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:39,737 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:45:39,786 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:39,786 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:45:39,831 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:45:39,831 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:45:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:45:39 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:45:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:45:41 - docling.document_converter - Going to convert document batch... -INFO: 04:45:41 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 44834b4eb26b8d8aa7ba8a2194d47d80 -INFO: 04:45:41 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:45:41 - docling.document_converter - Finished converting document file in 0.60 sec. +INFO: 04:42:18 - docling_jobkit.convert.results - Processed 1 docs in 0.35 seconds. +INFO: 04:42:18 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 70ec8758-5f88-4bf5-ab5f-c71b6a4a2741 in 0.35 seconds +INFO: 04:42:19 - uvicorn.access - 172.17.0.1:60724 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:42:19 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:42:19 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:42:19 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:42:19 - docling_serve.app - [TENANT_ID] Task 2cbeee39-cf6a-4453-9930-9e2245e8aa14 created with tenant_id='default' +INFO: 04:42:19 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 2cbeee39-cf6a-4453-9930-9e2245e8aa14 +INFO: 04:42:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:42:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 0d91e423d19d6a68575e0f3ea18edfc6 +INFO: 04:42:19 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:42:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:42:19,401 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:19,401 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:42:19,443 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:19,443 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:42:19,508 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:19,508 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:42:19 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:42:19 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:42:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:42:20 - docling.document_converter - Going to convert document batch... +INFO: 04:42:20 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 0d91e423d19d6a68575e0f3ea18edfc6 +INFO: 04:42:20 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:42:20 - docling.document_converter - Finished converting document file in 0.22 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:675: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:45:41 - docling_jobkit.convert.results - Processed 1 docs in 0.63 seconds. -INFO: 04:45:41 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 92343079-3be5-40e2-972b-a23b6e6d4deb in 0.63 seconds -INFO: 04:45:43 - uvicorn.access - 172.17.0.1:57624 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:45:43 - uvicorn.access - 172.17.0.1:57624 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:45:43 - uvicorn.access - 172.17.0.1:57624 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:42:20 - docling_jobkit.convert.results - Processed 1 docs in 0.26 seconds. +INFO: 04:42:20 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2cbeee39-cf6a-4453-9930-9e2245e8aa14 in 0.26 seconds +INFO: 04:42:21 - uvicorn.access - 172.17.0.1:60724 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:42:21 - uvicorn.access - 172.17.0.1:60724 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:42:21 - uvicorn.access - 172.17.0.1:60724 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -910,152 +910,152 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:43:41 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:41 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:43:41 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:43:41 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:43:41 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:43:41 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:43:41 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:43:41 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:43:41 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:43:41 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:43:41 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:43:41 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:43:41 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:43:41 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/livez$,/health$,/metrics$,/readyz$,/ready$) -INFO: 04:43:42 - uvicorn.error - Started server process [1] -INFO: 04:43:42 - uvicorn.error - Waiting for application startup. -INFO: 04:43:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:44 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:43:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:45 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:43:45 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:43:45 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 246a8611dcb8660b3c8fd9757a157fd3 -INFO: 04:43:45 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:43:45 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:43:45 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:43:45.285035281 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:43:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:43:45,752 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:45,753 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:43:45,826 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:45,827 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:43:45,871 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:45,872 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:43:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:43:45 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:43:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:43:49 - docling.document_converter - Going to convert document batch... -INFO: 04:43:49 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 98c4104a248971954a47caf8013545f3 -INFO: 04:43:49 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:43:49 - docling.document_converter - Finished converting document file in 0.51 sec. +INFO: 04:41:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:41:50 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:41:50 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:41:55 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:41:55 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:41:55 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:41:55 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:41:55 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:41:55 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:41:55 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:41:55 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:41:55 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:41:55 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:41:55 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/ready$,/health$,/livez$,/readyz$,/healthz$) +INFO: 04:41:55 - uvicorn.error - Started server process [1] +INFO: 04:41:55 - uvicorn.error - Waiting for application startup. +INFO: 04:42:02 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:42:02 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:42:02 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:42:02 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:42:02 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:42:03 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash cca6cc8a4b628ed50237f2b82843a142 +INFO: 04:42:03 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:42:03 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:42:03 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:42:03.122387762 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:42:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:42:03,695 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:03,697 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:42:03,783 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:03,783 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:42:03,813 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:03,814 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:42:03 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:42:03 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:42:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:42:06 - docling.document_converter - Going to convert document batch... +INFO: 04:42:06 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 03faa955d692daf69974ff9d6d71a0b0 +INFO: 04:42:06 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:42:06 - docling.document_converter - Finished converting document file in 0.46 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:43:49 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. -INFO: 04:43:49 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job d3af9bfe-4f00-4461-90ec-0bb229f65f12 in 0.58 seconds -INFO: 04:43:49 - uvicorn.access - 172.17.0.1:41150 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:43:49 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:43:49 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:43:49 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:43:49 - docling_serve.app - [TENANT_ID] Task ac84de27-284f-4d38-9cb8-0dba298d978a created with tenant_id='default' -INFO: 04:43:49 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task ac84de27-284f-4d38-9cb8-0dba298d978a -INFO: 04:43:49 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:43:49 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 98c4104a248971954a47caf8013545f3 -INFO: 04:43:49 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:43:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:43:49,743 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:49,744 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:43:49,795 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:49,795 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:43:49,835 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:49,835 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:43:49 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:43:49 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:43:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:43:51 - docling.document_converter - Going to convert document batch... -INFO: 04:43:51 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 98c4104a248971954a47caf8013545f3 -INFO: 04:43:51 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:43:51 - docling.document_converter - Finished converting document file in 0.74 sec. +INFO: 04:42:06 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. +INFO: 04:42:06 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 3323a7a2-7751-4a77-9346-3f40e7009338 in 0.51 seconds +INFO: 04:42:07 - uvicorn.access - 172.17.0.1:52552 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:42:07 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:42:07 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:42:07 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:42:07 - docling_serve.app - [TENANT_ID] Task 6d0e2a75-f7f1-4b6e-801a-a4875b09cd65 created with tenant_id='default' +INFO: 04:42:07 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 6d0e2a75-f7f1-4b6e-801a-a4875b09cd65 +INFO: 04:42:07 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:42:07 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 03faa955d692daf69974ff9d6d71a0b0 +INFO: 04:42:07 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:42:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:42:07,341 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:07,341 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:42:07,420 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:07,420 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:42:07,462 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:07,463 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:42:07 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:42:07 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:42:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:42:08 - docling.document_converter - Going to convert document batch... +INFO: 04:42:08 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 03faa955d692daf69974ff9d6d71a0b0 +INFO: 04:42:08 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:42:08 - docling.document_converter - Finished converting document file in 0.38 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:43:51 - docling_jobkit.convert.results - Processed 1 docs in 0.74 seconds. -INFO: 04:43:51 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job ac84de27-284f-4d38-9cb8-0dba298d978a in 0.74 seconds -INFO: 04:43:51 - uvicorn.access - 172.17.0.1:41150 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:43:51 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:43:51 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:43:51 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:43:51 - docling_serve.app - [TENANT_ID] Task f003c4fa-2008-4c1b-a834-bb78c8e37a70 created with tenant_id='default' -INFO: 04:43:51 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task f003c4fa-2008-4c1b-a834-bb78c8e37a70 -INFO: 04:43:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:43:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e48a657870181f94de2cf18f13159d2a -INFO: 04:43:51 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:43:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:43:51,736 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:51,737 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:43:51,784 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:51,784 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:43:51,830 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:43:51,831 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:43:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:43:51 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:43:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:43:52 - docling.document_converter - Going to convert document batch... -INFO: 04:43:52 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash e48a657870181f94de2cf18f13159d2a -INFO: 04:43:52 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:43:53 - docling.document_converter - Finished converting document file in 0.49 sec. +INFO: 04:42:08 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 04:42:08 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 6d0e2a75-f7f1-4b6e-801a-a4875b09cd65 in 0.38 seconds +INFO: 04:42:09 - uvicorn.access - 172.17.0.1:52552 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:42:09 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:42:09 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:42:09 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:42:09 - docling_serve.app - [TENANT_ID] Task 329e6a00-fc04-4a30-82e6-d22af9d34f19 created with tenant_id='default' +INFO: 04:42:09 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 329e6a00-fc04-4a30-82e6-d22af9d34f19 +INFO: 04:42:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:42:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 18c327a101927e89bba2d9e2190705a9 +INFO: 04:42:09 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:42:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:42:09,712 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:09,712 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:42:09,750 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:09,750 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:42:09,785 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:42:09,785 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:42:09 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:42:09 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:42:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:42:10 - docling.document_converter - Going to convert document batch... +INFO: 04:42:10 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 18c327a101927e89bba2d9e2190705a9 +INFO: 04:42:10 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:42:10 - docling.document_converter - Finished converting document file in 0.32 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:43:53 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. -INFO: 04:43:53 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f003c4fa-2008-4c1b-a834-bb78c8e37a70 in 0.52 seconds -INFO: 04:43:53 - uvicorn.access - 172.17.0.1:41150 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:43:53 - uvicorn.access - 172.17.0.1:41150 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:43:53 - uvicorn.access - 172.17.0.1:41150 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:42:10 - docling_jobkit.convert.results - Processed 1 docs in 0.34 seconds. +INFO: 04:42:10 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 329e6a00-fc04-4a30-82e6-d22af9d34f19 in 0.34 seconds +INFO: 04:42:11 - uvicorn.access - 172.17.0.1:52552 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:42:11 - uvicorn.access - 172.17.0.1:52552 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:42:11 - uvicorn.access - 172.17.0.1:52552 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1093,153 +1093,153 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:42:06 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:06 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:42:06 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:42:07 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:42:07 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:42:07 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:42:07 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:42:07 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:42:07 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:42:07 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:42:07 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. -INFO: 04:42:07 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:42:07 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:42:07 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/health$,/ready$,/healthz$,/livez$,/readyz$) -INFO: 04:42:07 - uvicorn.error - Started server process [1] -INFO: 04:42:07 - uvicorn.error - Waiting for application startup. -INFO: 04:42:09 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:10 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:42:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:10 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:42:10 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:42:10 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b -INFO: 04:42:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:42:10 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:42:10 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:42:10.456995444 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:42:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:42:10,915 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:10,916 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:42:10,973 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:10,974 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:42:11,014 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:11,015 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:42:11 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:42:11 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:42:11 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:42:13 - docling.document_converter - Going to convert document batch... -INFO: 04:42:13 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:42:13 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:42:13 - docling.document_converter - Finished converting document file in 0.64 sec. +INFO: 04:38:17 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:17 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:38:17 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:38:18 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:38:18 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxSourceProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:38:18 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:38:18 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:38:18 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:38:18 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:38:18 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:38:18 - docling_jobkit.connectors.plugins.defaults - Connector 'BoxTargetProcessor' skipped — optional dependency not installed (No module named 'box_sdk_gen'). Install the matching extra to enable it. +INFO: 04:38:18 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:38:18 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:38:18 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/healthz$,/health$,/readyz$,/livez$,/ready$) +INFO: 04:38:18 - uvicorn.error - Started server process [1] +INFO: 04:38:18 - uvicorn.error - Waiting for application startup. +INFO: 04:38:21 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:22 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:38:22 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:22 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:38:22 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:22 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b +INFO: 04:38:22 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:22 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:38:22 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:38:22.543640408 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:38:22 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:38:23,091 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:23,092 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:38:23,416 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:23,416 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:38:23,446 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:23,447 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:38:23 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:23 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:26 - docling.document_converter - Going to convert document batch... +INFO: 04:38:26 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:38:26 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:26 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:42:14 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:42:14 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. -INFO: 04:42:14 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ec1c88a5-1c3c-4a44-bbc4-01fd71d9f601 in 0.70 seconds -INFO: 04:42:14 - uvicorn.access - 172.17.0.1:58838 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:42:14 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:42:14 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:42:14 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:42:14 - docling_serve.app - [TENANT_ID] Task 30f72dc3-b461-4207-9b14-5ea6a9da149e created with tenant_id='default' -INFO: 04:42:14 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 30f72dc3-b461-4207-9b14-5ea6a9da149e -INFO: 04:42:14 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:42:14 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:42:14 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:42:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:42:14,464 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:14,464 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:42:14,538 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:14,538 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:42:14,578 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:14,578 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:42:14 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:42:14 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:42:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:42:16 - docling.document_converter - Going to convert document batch... -INFO: 04:42:16 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:42:16 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:42:16 - docling.document_converter - Finished converting document file in 0.83 sec. +WARNING: 04:38:26 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:38:26 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 04:38:26 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 070a7783-bbfa-41f9-b430-440d2113f5f8 in 0.46 seconds +INFO: 04:38:26 - uvicorn.access - 172.17.0.1:36732 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:26 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:38:26 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:38:26 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:38:26 - docling_serve.app - [TENANT_ID] Task ab506275-a48a-4add-98f0-fc995a3e2c45 created with tenant_id='default' +INFO: 04:38:26 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task ab506275-a48a-4add-98f0-fc995a3e2c45 +INFO: 04:38:26 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:27 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:38:27 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:38:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:38:27,100 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:27,100 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:38:27,142 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:27,143 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:38:27,173 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:27,173 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:38:27 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:27 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:28 - docling.document_converter - Going to convert document batch... +INFO: 04:38:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:38:28 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:28 - docling.document_converter - Finished converting document file in 0.25 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:42:16 - docling_jobkit.convert.results - Processed 1 docs in 0.84 seconds. -INFO: 04:42:16 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 30f72dc3-b461-4207-9b14-5ea6a9da149e in 0.84 seconds -INFO: 04:42:16 - uvicorn.access - 172.17.0.1:58838 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:42:16 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:42:16 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:42:16 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:42:16 - docling_serve.app - [TENANT_ID] Task e4b25da6-0813-4199-a404-9510bfaeac9f created with tenant_id='default' -INFO: 04:42:16 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e4b25da6-0813-4199-a404-9510bfaeac9f -INFO: 04:42:16 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:42:16 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:42:16 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:42:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:42:16,467 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:16,467 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:42:16,519 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:16,519 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:42:16,576 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:42:16,576 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:42:16 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:42:16 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:42:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:42:17 - docling.document_converter - Going to convert document batch... -INFO: 04:42:17 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:42:17 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:42:17 - docling.document_converter - Finished converting document file in 0.47 sec. +INFO: 04:38:28 - docling_jobkit.convert.results - Processed 1 docs in 0.26 seconds. +INFO: 04:38:28 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job ab506275-a48a-4add-98f0-fc995a3e2c45 in 0.26 seconds +INFO: 04:38:28 - uvicorn.access - 172.17.0.1:36732 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:28 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:38:28 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:38:28 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:38:28 - docling_serve.app - [TENANT_ID] Task e70a90f4-fd99-4b33-a0f5-e9b5b0b6c2f5 created with tenant_id='default' +INFO: 04:38:28 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e70a90f4-fd99-4b33-a0f5-e9b5b0b6c2f5 +INFO: 04:38:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:29 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:38:29 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:38:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:38:29,520 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:29,520 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:38:29,560 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:29,561 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:38:29,605 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:29,605 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:38:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:29 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:30 - docling.document_converter - Going to convert document batch... +INFO: 04:38:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:38:30 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:30 - docling.document_converter - Finished converting document file in 0.23 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:661: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:42:17 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:42:17 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e4b25da6-0813-4199-a404-9510bfaeac9f in 0.51 seconds -INFO: 04:42:18 - uvicorn.access - 172.17.0.1:58838 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:42:18 - uvicorn.access - 172.17.0.1:58838 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:42:18 - uvicorn.access - 172.17.0.1:58838 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:38:30 - docling_jobkit.convert.results - Processed 1 docs in 0.26 seconds. +INFO: 04:38:30 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e70a90f4-fd99-4b33-a0f5-e9b5b0b6c2f5 in 0.26 seconds +INFO: 04:38:30 - uvicorn.access - 172.17.0.1:36732 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:31 - uvicorn.access - 172.17.0.1:36732 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:38:31 - uvicorn.access - 172.17.0.1:36732 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1277,151 +1277,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:40:18 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:18 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:40:18 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:40:18 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:40:18 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:40:18 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:40:18 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:40:18 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:40:18 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:40:18 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:40:18 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:40:18 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/livez$,/metrics$,/readyz$,/ready$) -INFO: 04:40:19 - uvicorn.error - Started server process [1] -INFO: 04:40:19 - uvicorn.error - Waiting for application startup. -INFO: 04:40:21 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:21 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:40:21 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:21 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:40:21 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:40:22 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b -INFO: 04:40:22 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:40:22 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:40:22 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:40:22.103360298 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:40:22 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:40:22,322 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:22,323 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:40:22,381 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:22,382 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:40:22,421 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:22,422 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:40:22 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:40:22 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:40:22 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:40:25 - docling.document_converter - Going to convert document batch... -INFO: 04:40:25 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:40:25 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:40:25 - docling.document_converter - Finished converting document file in 0.50 sec. +INFO: 04:38:11 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:11 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:38:11 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:38:12 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:38:12 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:38:12 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:38:12 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:38:12 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:38:12 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:38:12 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:38:12 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:38:12 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/healthz$,/ready$,/health$,/metrics$,/readyz$) +INFO: 04:38:12 - uvicorn.error - Started server process [1] +INFO: 04:38:12 - uvicorn.error - Waiting for application startup. +INFO: 04:38:15 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:16 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:38:16 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:16 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:38:16 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:16 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4b071d1415ad1ebea85cea80f4d6fa7b +INFO: 04:38:16 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:38:16 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:38:16 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:38:16.342478314 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:38:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:38:16,546 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:16,547 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:38:16,649 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:16,649 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:38:16,684 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:16,685 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:38:16 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:16 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:20 - docling.document_converter - Going to convert document batch... +INFO: 04:38:20 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:38:20 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:20 - docling.document_converter - Finished converting document file in 0.39 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:655: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:40:25 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:40:25 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. -INFO: 04:40:25 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 00460db5-f3b7-4331-9fbb-1de3482f0f76 in 0.58 seconds -INFO: 04:40:26 - uvicorn.access - 172.17.0.1:39764 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:40:26 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:40:26 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:40:26 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:40:26 - docling_serve.app - [TENANT_ID] Task 5184ebab-68e9-44d0-84a9-9bbf76cfc630 created with tenant_id='default' -INFO: 04:40:26 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5184ebab-68e9-44d0-84a9-9bbf76cfc630 -INFO: 04:40:26 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:40:26 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:40:26 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:40:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:40:26,546 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:26,546 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:40:26,600 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:26,600 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:40:26,637 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:26,638 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:40:26 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:40:26 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:40:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:40:27 - docling.document_converter - Going to convert document batch... -INFO: 04:40:27 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 -INFO: 04:40:27 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:40:27 - docling.document_converter - Finished converting document file in 0.48 sec. +WARNING: 04:38:20 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:38:20 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. +INFO: 04:38:20 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ef504eda-cbe7-4233-9cf3-84cc390d701c in 0.45 seconds +INFO: 04:38:20 - uvicorn.access - 172.17.0.1:51912 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:20 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:38:20 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:38:20 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:38:20 - docling_serve.app - [TENANT_ID] Task 5de786b7-3093-4989-8df7-2b13d60ee4a7 created with tenant_id='default' +INFO: 04:38:20 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5de786b7-3093-4989-8df7-2b13d60ee4a7 +INFO: 04:38:20 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:21 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:38:21 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:38:21 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:38:21,107 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:21,107 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:38:21,150 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:21,150 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:38:21,208 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:21,208 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:38:21 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:21 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:21 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:22 - docling.document_converter - Going to convert document batch... +INFO: 04:38:22 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a2e22ed4b71003a02ccc48074bc1ab74 +INFO: 04:38:22 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:22 - docling.document_converter - Finished converting document file in 0.50 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:655: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:40:27 - docling_jobkit.convert.results - Processed 1 docs in 0.49 seconds. -INFO: 04:40:27 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5184ebab-68e9-44d0-84a9-9bbf76cfc630 in 0.49 seconds -INFO: 04:40:28 - uvicorn.access - 172.17.0.1:39764 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:40:28 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:40:28 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:40:28 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:40:28 - docling_serve.app - [TENANT_ID] Task 227eb15b-4431-484f-9df0-ae282d83fbcc created with tenant_id='default' -INFO: 04:40:28 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 227eb15b-4431-484f-9df0-ae282d83fbcc -INFO: 04:40:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:40:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:40:28 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:40:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:40:28,551 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:28,551 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:40:28,600 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:28,601 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:40:28,648 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:40:28,649 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:40:28 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:40:28 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:40:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:40:30 - docling.document_converter - Going to convert document batch... -INFO: 04:40:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b -INFO: 04:40:30 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:40:30 - docling.document_converter - Finished converting document file in 0.46 sec. +INFO: 04:38:22 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. +INFO: 04:38:22 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5de786b7-3093-4989-8df7-2b13d60ee4a7 in 0.51 seconds +INFO: 04:38:22 - uvicorn.access - 172.17.0.1:51912 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:23 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:38:23 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:38:23 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:38:23 - docling_serve.app - [TENANT_ID] Task e187ea47-60ba-4566-81fb-fee3e07040bf created with tenant_id='default' +INFO: 04:38:23 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e187ea47-60ba-4566-81fb-fee3e07040bf +INFO: 04:38:23 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:38:23 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:38:23 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:38:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:38:23,139 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:23,139 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:38:23,177 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:23,177 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:38:23,222 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:38:23,222 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:38:23 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:38:23 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:38:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:38:24 - docling.document_converter - Going to convert document batch... +INFO: 04:38:24 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 78cb5ade368814d0813875c101ee149b +INFO: 04:38:24 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:38:24 - docling.document_converter - Finished converting document file in 0.42 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:655: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:40:30 - docling_jobkit.convert.results - Processed 1 docs in 0.49 seconds. -INFO: 04:40:30 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 227eb15b-4431-484f-9df0-ae282d83fbcc in 0.49 seconds -INFO: 04:40:30 - uvicorn.access - 172.17.0.1:39764 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:40:30 - uvicorn.access - 172.17.0.1:39764 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:40:30 - uvicorn.access - 172.17.0.1:39764 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:38:24 - docling_jobkit.convert.results - Processed 1 docs in 0.44 seconds. +INFO: 04:38:24 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e187ea47-60ba-4566-81fb-fee3e07040bf in 0.44 seconds +INFO: 04:38:25 - uvicorn.access - 172.17.0.1:51912 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:38:25 - uvicorn.access - 172.17.0.1:51912 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:38:25 - uvicorn.access - 172.17.0.1:51912 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1459,151 +1459,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:38:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:33 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:38:33 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:38:33 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:38:33 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:38:33 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:38:33 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:38:33 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:38:33 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:38:34 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:38:34 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:38:34 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/ready$,/readyz$,/metrics$,/livez$) -INFO: 04:38:34 - uvicorn.error - Started server process [1] -INFO: 04:38:34 - uvicorn.error - Waiting for application startup. -INFO: 04:38:36 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:36 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:38:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:37 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:38:37 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:38:37 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 019ac48c98c19d19127e62d9a66de678 -INFO: 04:38:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:38:37 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:38:37 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:38:37.145675166 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:38:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:38:37,355 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:37,356 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:38:37,411 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:37,412 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:38:37,457 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:37,457 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:38:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:38:37 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:38:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:38:40 - docling.document_converter - Going to convert document batch... -INFO: 04:38:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd -INFO: 04:38:40 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:38:40 - docling.document_converter - Finished converting document file in 0.75 sec. +INFO: 04:34:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:54 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:34:54 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:34:55 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:34:55 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:34:55 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:34:55 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:34:55 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:34:55 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:34:55 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:34:55 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:34:55 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/metrics$,/readyz$,/livez$,/ready$) +INFO: 04:34:55 - uvicorn.error - Started server process [1] +INFO: 04:34:55 - uvicorn.error - Waiting for application startup. +INFO: 04:34:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:59 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:34:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:59 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:34:59 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:34:59 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 019ac48c98c19d19127e62d9a66de678 +INFO: 04:34:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:59 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:34:59 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:35:00.103429721 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:35:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:35:00,516 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:00,518 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:35:00,751 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:00,751 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:35:00,808 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:00,808 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:35:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:35:00 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:35:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:35:04 - docling.document_converter - Going to convert document batch... +INFO: 04:35:04 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd +INFO: 04:35:04 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:35:04 - docling.document_converter - Finished converting document file in 0.45 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:645: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:38:40 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:38:40 - docling_jobkit.convert.results - Processed 1 docs in 0.82 seconds. -INFO: 04:38:40 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 44ec17bc-0d5d-4bd5-83ab-ed6b6ba72597 in 0.82 seconds -INFO: 04:38:42 - uvicorn.access - 172.17.0.1:47268 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:38:42 - docling_serve.app - [TENANT_ID] Task 3bcf1d09-401d-4379-bf78-9631306f54bd created with tenant_id='default' -INFO: 04:38:42 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 3bcf1d09-401d-4379-bf78-9631306f54bd -INFO: 04:38:42 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:38:42 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd -INFO: 04:38:42 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:38:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:38:42,880 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:42,880 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:38:42,933 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:42,933 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:38:42,973 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:42,973 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:38:43 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:38:43 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:38:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:38:44 - docling.document_converter - Going to convert document batch... -INFO: 04:38:44 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd -INFO: 04:38:44 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:38:44 - docling.document_converter - Finished converting document file in 0.55 sec. +WARNING: 04:35:04 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:35:04 - docling_jobkit.convert.results - Processed 1 docs in 0.54 seconds. +INFO: 04:35:04 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c2997b5b-621f-4446-95ea-6eebbe873dd5 in 0.54 seconds +INFO: 04:35:04 - uvicorn.access - 172.17.0.1:58824 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:35:04 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:35:04 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:35:04 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:35:04 - docling_serve.app - [TENANT_ID] Task 08408909-9c70-4e81-b68a-16408b6faec3 created with tenant_id='default' +INFO: 04:35:04 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 08408909-9c70-4e81-b68a-16408b6faec3 +INFO: 04:35:04 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:35:04 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd +INFO: 04:35:04 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:35:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:35:04,913 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:04,913 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:35:04,994 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:04,994 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:35:05,034 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:05,037 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:35:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:35:05 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:35:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:35:06 - docling.document_converter - Going to convert document batch... +INFO: 04:35:06 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 6b5aa9d49bf5933a22591c3559b94bfd +INFO: 04:35:06 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:35:06 - docling.document_converter - Finished converting document file in 0.33 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:645: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:38:44 - docling_jobkit.convert.results - Processed 1 docs in 0.55 seconds. -INFO: 04:38:44 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 3bcf1d09-401d-4379-bf78-9631306f54bd in 0.55 seconds -INFO: 04:38:44 - uvicorn.access - 172.17.0.1:47268 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:38:44 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:38:44 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:38:44 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:38:44 - docling_serve.app - [TENANT_ID] Task 71eae667-7e6f-4ca7-b77b-a0498765c670 created with tenant_id='default' -INFO: 04:38:44 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 71eae667-7e6f-4ca7-b77b-a0498765c670 -INFO: 04:38:44 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:38:44 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 345bf8d309571831952bb6d347d0f005 -INFO: 04:38:44 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:38:44 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:38:44,910 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:44,910 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:38:44,966 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:44,966 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:38:45,007 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:38:45,008 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:38:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:38:45 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:38:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:38:46 - docling.document_converter - Going to convert document batch... -INFO: 04:38:46 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 345bf8d309571831952bb6d347d0f005 -INFO: 04:38:46 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:38:46 - docling.document_converter - Finished converting document file in 0.46 sec. +INFO: 04:35:06 - docling_jobkit.convert.results - Processed 1 docs in 0.33 seconds. +INFO: 04:35:06 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 08408909-9c70-4e81-b68a-16408b6faec3 in 0.33 seconds +INFO: 04:35:06 - uvicorn.access - 172.17.0.1:58824 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:35:06 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:35:06 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:35:06 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:35:06 - docling_serve.app - [TENANT_ID] Task e5fc4551-5913-45f6-b954-9f7d3725ee54 created with tenant_id='default' +INFO: 04:35:06 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e5fc4551-5913-45f6-b954-9f7d3725ee54 +INFO: 04:35:06 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:35:06 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 345bf8d309571831952bb6d347d0f005 +INFO: 04:35:06 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:35:06 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:35:06,935 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:06,935 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:35:06,977 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:06,977 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:35:07,043 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:07,044 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:35:07 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:35:07 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:35:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:35:07 - docling.document_converter - Going to convert document batch... +INFO: 04:35:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 345bf8d309571831952bb6d347d0f005 +INFO: 04:35:07 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:35:07 - docling.document_converter - Finished converting document file in 0.24 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:645: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:38:46 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:38:46 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 71eae667-7e6f-4ca7-b77b-a0498765c670 in 0.50 seconds -INFO: 04:38:46 - uvicorn.access - 172.17.0.1:47268 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:38:47 - uvicorn.access - 172.17.0.1:47268 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:38:47 - uvicorn.access - 172.17.0.1:47268 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:35:07 - docling_jobkit.convert.results - Processed 1 docs in 0.27 seconds. +INFO: 04:35:07 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e5fc4551-5913-45f6-b954-9f7d3725ee54 in 0.27 seconds +INFO: 04:35:08 - uvicorn.access - 172.17.0.1:58824 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:35:09 - uvicorn.access - 172.17.0.1:58824 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:35:09 - uvicorn.access - 172.17.0.1:58824 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1641,151 +1641,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:37:01 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:37:01 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:37:01 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:37:01 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:37:01 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:37:01 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:37:01 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:37:01 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:37:01 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. -INFO: 04:37:01 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:37:01 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:37:01 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/metrics$,/healthz$,/ready$,/readyz$,/health$) -INFO: 04:37:02 - uvicorn.error - Started server process [1] -INFO: 04:37:02 - uvicorn.error - Waiting for application startup. -INFO: 04:37:04 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:37:05 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:37:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:37:05 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:37:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:37:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9d06178a9f1c8aeb9889d1e46440f3fa -INFO: 04:37:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:37:05 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:37:05 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:37:05.231326088 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:37:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:37:05,451 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:05,452 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:37:05,514 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:05,514 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:37:05,574 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:05,574 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:37:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:37:05 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:37:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:37:08 - docling.document_converter - Going to convert document batch... -INFO: 04:37:08 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d -INFO: 04:37:08 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:37:08 - docling.document_converter - Finished converting document file in 0.56 sec. +INFO: 04:34:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:49 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:34:49 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:34:50 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:34:50 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:34:50 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:34:50 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:34:50 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:34:50 - docling_jobkit.connectors.plugins.defaults - Connector 'KafkaTargetProcessor' skipped — optional dependency not installed (No module named 'confluent_kafka'). Install the matching extra to enable it. +INFO: 04:34:50 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:34:50 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:34:50 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/healthz$,/health$,/ready$,/metrics$) +INFO: 04:34:50 - uvicorn.error - Started server process [1] +INFO: 04:34:50 - uvicorn.error - Waiting for application startup. +INFO: 04:34:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:55 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:34:55 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:55 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:34:55 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:34:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9d06178a9f1c8aeb9889d1e46440f3fa +INFO: 04:34:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:34:56 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:34:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:34:56.150627920 [W:onnxruntime:Default, device_discovery.cc:146 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:34:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:34:56,357 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:34:56,359 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:34:56,575 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:34:56,575 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:34:56,607 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:34:56,608 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:34:56 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:34:56 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:34:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:35:01 - docling.document_converter - Going to convert document batch... +INFO: 04:35:01 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d +INFO: 04:35:01 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:35:01 - docling.document_converter - Finished converting document file in 0.41 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:641: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:37:08 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:37:08 - docling_jobkit.convert.results - Processed 1 docs in 0.62 seconds. -INFO: 04:37:08 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 7149d429-bf4a-4ab9-a264-2a70bd642210 in 0.62 seconds -INFO: 04:37:08 - uvicorn.access - 172.17.0.1:59436 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:37:08 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:37:08 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:37:08 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:37:08 - docling_serve.app - [TENANT_ID] Task 17f3364d-d484-4fa4-bf18-4540e54e1e2c created with tenant_id='default' -INFO: 04:37:08 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 17f3364d-d484-4fa4-bf18-4540e54e1e2c -INFO: 04:37:08 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:37:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d -INFO: 04:37:09 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:37:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:37:09,027 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:09,028 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:37:09,081 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:09,082 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:37:09,129 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:09,130 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:37:09 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:37:09 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:37:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:37:10 - docling.document_converter - Going to convert document batch... -INFO: 04:37:10 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d -INFO: 04:37:10 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:37:10 - docling.document_converter - Finished converting document file in 0.49 sec. +WARNING: 04:35:01 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:35:01 - docling_jobkit.convert.results - Processed 1 docs in 0.53 seconds. +INFO: 04:35:01 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 957a792e-137a-42bb-a83c-416add2f078d in 0.53 seconds +INFO: 04:35:01 - uvicorn.access - 172.17.0.1:37156 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:35:01 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:35:01 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:35:01 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:35:01 - docling_serve.app - [TENANT_ID] Task 35d475d0-8c67-4960-ad64-b7bf85b3971a created with tenant_id='default' +INFO: 04:35:01 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 35d475d0-8c67-4960-ad64-b7bf85b3971a +INFO: 04:35:01 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:35:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d +INFO: 04:35:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:35:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:35:01,943 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:01,944 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:35:02,051 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:02,051 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:35:02,090 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:02,090 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:35:02 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:35:02 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:35:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:35:03 - docling.document_converter - Going to convert document batch... +INFO: 04:35:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash a1d02772fb798c5f3e06aa82e0d32e7d +INFO: 04:35:03 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:35:03 - docling.document_converter - Finished converting document file in 0.43 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:641: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:37:10 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:37:10 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 17f3364d-d484-4fa4-bf18-4540e54e1e2c in 0.50 seconds -INFO: 04:37:10 - uvicorn.access - 172.17.0.1:59436 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:37:10 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:37:10 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:37:10 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:37:10 - docling_serve.app - [TENANT_ID] Task 89a2908e-8ac4-48b1-a399-4c78860810fa created with tenant_id='default' -INFO: 04:37:10 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 89a2908e-8ac4-48b1-a399-4c78860810fa -INFO: 04:37:10 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:37:11 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 -INFO: 04:37:11 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:37:11 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:37:11,036 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:11,036 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:37:11,089 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:11,089 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:37:11,135 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:37:11,135 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:37:11 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:37:11 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:37:11 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:37:12 - docling.document_converter - Going to convert document batch... -INFO: 04:37:12 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 -INFO: 04:37:12 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:37:12 - docling.document_converter - Finished converting document file in 0.47 sec. +INFO: 04:35:03 - docling_jobkit.convert.results - Processed 1 docs in 0.44 seconds. +INFO: 04:35:03 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 35d475d0-8c67-4960-ad64-b7bf85b3971a in 0.44 seconds +INFO: 04:35:03 - uvicorn.access - 172.17.0.1:37156 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:35:03 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:35:03 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:35:03 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:35:03 - docling_serve.app - [TENANT_ID] Task 0dc46acf-4de5-4dc9-b1d0-c0c1e52f4e6b created with tenant_id='default' +INFO: 04:35:03 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 0dc46acf-4de5-4dc9-b1d0-c0c1e52f4e6b +INFO: 04:35:03 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:35:03 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 +INFO: 04:35:03 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:35:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:35:03,936 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:03,936 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:35:04,000 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:04,001 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:35:04,033 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:35:04,033 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:35:04 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:35:04 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:35:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:35:04 - docling.document_converter - Going to convert document batch... +INFO: 04:35:04 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 21c1cdafbd5b48f9b0cfcb806e9e9d57 +INFO: 04:35:04 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:35:05 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:641: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:37:12 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:37:12 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 89a2908e-8ac4-48b1-a399-4c78860810fa in 0.50 seconds -INFO: 04:37:12 - uvicorn.access - 172.17.0.1:59436 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:37:13 - uvicorn.access - 172.17.0.1:59436 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:37:13 - uvicorn.access - 172.17.0.1:59436 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:35:05 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 04:35:05 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 0dc46acf-4de5-4dc9-b1d0-c0c1e52f4e6b in 0.39 seconds +INFO: 04:35:05 - uvicorn.access - 172.17.0.1:37156 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:35:06 - uvicorn.access - 172.17.0.1:37156 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:35:06 - uvicorn.access - 172.17.0.1:37156 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -1823,151 +1823,151 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:35:21 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:35:21 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:35:21 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:35:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:35:21 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:35:21 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:35:21 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. -INFO: 04:35:21 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. -INFO: 04:35:21 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:35:21 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:35:21 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/health$,/livez$,/readyz$,/healthz$,/ready$) -INFO: 04:35:21 - uvicorn.error - Started server process [1] -INFO: 04:35:21 - uvicorn.error - Waiting for application startup. -INFO: 04:35:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:35:24 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:35:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:35:24 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:35:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:35:24 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e2db689ab35ca52a08b5b7fa25de8cc8 -INFO: 04:35:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:35:24 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:35:24 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:35:24.986407487 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:35:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:35:25,208 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:25,209 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:35:25,264 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:25,265 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:35:25,304 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:25,304 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:35:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:35:25 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:35:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +INFO: 04:31:43 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:43 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:31:43 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:31:44 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointSourceProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:31:44 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:31:44 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:31:44 - docling_jobkit.connectors.plugins.defaults - Connector 'AstraDBTargetProcessor' skipped — optional dependency not installed (No module named 'astrapy'). Install the matching extra to enable it. +INFO: 04:31:44 - docling_jobkit.connectors.plugins.defaults - Connector 'SharePointTargetProcessor' skipped — optional dependency not installed (No module named 'office365'). Install the matching extra to enable it. +INFO: 04:31:45 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:31:45 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:31:45 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/readyz$,/metrics$,/health$,/livez$,/ready$) +INFO: 04:31:45 - uvicorn.error - Started server process [1] +INFO: 04:31:45 - uvicorn.error - Waiting for application startup. +INFO: 04:31:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:50 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:31:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:50 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:31:50 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:50 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e2db689ab35ca52a08b5b7fa25de8cc8 +INFO: 04:31:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:50 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:31:50 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:31:50.489861464 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:31:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:31:50,816 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:50,818 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:31:50,951 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:50,951 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:31:50,981 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:50,981 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:31:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:51 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:31:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' [transformers] `torch_dtype` is deprecated! Use `dtype` instead! - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:35:29 - docling.document_converter - Going to convert document batch... -INFO: 04:35:29 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d -INFO: 04:35:29 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:35:29 - docling.document_converter - Finished converting document file in 0.50 sec. + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:55 - docling.document_converter - Going to convert document batch... +INFO: 04:31:55 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d +INFO: 04:31:55 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:55 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:635: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:35:29 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:35:29 - docling_jobkit.convert.results - Processed 1 docs in 0.56 seconds. -INFO: 04:35:29 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 9f7a31c4-22e5-4350-97f7-670e15dad2b8 in 0.56 seconds -INFO: 04:35:29 - uvicorn.access - 172.17.0.1:55938 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:35:29 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:35:29 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:35:29 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:35:29 - docling_serve.app - [TENANT_ID] Task 4f81fb03-98d9-4eb1-b602-d059c653a021 created with tenant_id='default' -INFO: 04:35:29 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 4f81fb03-98d9-4eb1-b602-d059c653a021 -INFO: 04:35:29 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:35:29 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d -INFO: 04:35:29 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:35:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:35:30,006 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:30,006 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:35:30,063 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:30,063 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:35:30,105 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:30,105 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:35:30 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:35:30 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:35:30 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:35:31 - docling.document_converter - Going to convert document batch... -INFO: 04:35:31 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d -INFO: 04:35:31 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:35:31 - docling.document_converter - Finished converting document file in 0.98 sec. +WARNING: 04:31:55 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:31:55 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 04:31:55 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 9912d84d-1e56-4eec-ac19-28fb9fc6d470 in 0.43 seconds +INFO: 04:31:56 - uvicorn.access - 172.17.0.1:39464 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:56 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:31:56 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:31:56 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:31:56 - docling_serve.app - [TENANT_ID] Task 3904c47c-83b1-4e18-8559-f7beb2a75fcf created with tenant_id='default' +INFO: 04:31:56 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 3904c47c-83b1-4e18-8559-f7beb2a75fcf +INFO: 04:31:56 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d +INFO: 04:31:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:31:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:31:56,529 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:56,529 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:31:56,572 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:56,572 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:31:56,632 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:56,632 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:31:56 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:56 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:31:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:58 - docling.document_converter - Going to convert document batch... +INFO: 04:31:58 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 5cd3e3811d2e4d7d996fcfcbbe327b1d +INFO: 04:31:58 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:58 - docling.document_converter - Finished converting document file in 0.47 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:635: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:35:31 - docling_jobkit.convert.results - Processed 1 docs in 0.98 seconds. -INFO: 04:35:31 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 4f81fb03-98d9-4eb1-b602-d059c653a021 in 0.98 seconds -INFO: 04:35:31 - uvicorn.access - 172.17.0.1:55938 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:35:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:35:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:35:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:35:31 - docling_serve.app - [TENANT_ID] Task b6d39001-23f1-4dce-ae0b-7f8ca3508b11 created with tenant_id='default' -INFO: 04:35:31 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task b6d39001-23f1-4dce-ae0b-7f8ca3508b11 -INFO: 04:35:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:35:32 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 -INFO: 04:35:32 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:35:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:35:32,030 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:32,030 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:35:32,083 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:32,084 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:35:32,123 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:35:32,124 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx -INFO: 04:35:32 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:35:32 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine -INFO: 04:35:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:35:33 - docling.document_converter - Going to convert document batch... -INFO: 04:35:33 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 -INFO: 04:35:33 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:35:33 - docling.document_converter - Finished converting document file in 0.46 sec. +INFO: 04:31:58 - docling_jobkit.convert.results - Processed 1 docs in 0.48 seconds. +INFO: 04:31:58 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 3904c47c-83b1-4e18-8559-f7beb2a75fcf in 0.48 seconds +INFO: 04:31:58 - uvicorn.access - 172.17.0.1:39464 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:58 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:31:58 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:31:58 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:31:58 - docling_serve.app - [TENANT_ID] Task 1ca96715-3df2-4521-b6a8-6e46ccac058e created with tenant_id='default' +INFO: 04:31:58 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 1ca96715-3df2-4521-b6a8-6e46ccac058e +INFO: 04:31:58 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:58 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 +INFO: 04:31:58 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:31:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:31:58,533 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:58,533 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:31:58,588 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:58,589 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:31:58,619 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:58,620 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/PP-OCRv6_rec_small.onnx +INFO: 04:31:58 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:58 - docling.models.inference_engines.object_detection.transformers_engine - Initializing Transformers object-detection engine +INFO: 04:31:58 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:59 - docling.document_converter - Going to convert document batch... +INFO: 04:31:59 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 9df8df3fc03c33cf6e8bd583e67dce64 +INFO: 04:31:59 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:59 - docling.document_converter - Finished converting document file in 0.34 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:635: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:35:33 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 04:35:33 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b6d39001-23f1-4dce-ae0b-7f8ca3508b11 in 0.50 seconds -INFO: 04:35:33 - uvicorn.access - 172.17.0.1:55938 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:35:34 - uvicorn.access - 172.17.0.1:55938 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:35:34 - uvicorn.access - 172.17.0.1:55938 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:31:59 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. +INFO: 04:31:59 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 1ca96715-3df2-4521-b6a8-6e46ccac058e in 0.37 seconds +INFO: 04:32:00 - uvicorn.access - 172.17.0.1:39464 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:32:00 - uvicorn.access - 172.17.0.1:39464 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:32:00 - uvicorn.access - 172.17.0.1:39464 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2005,139 +2005,139 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:33:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:46 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:33:46 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:33:47 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:33:47 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. -INFO: 04:33:47 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:33:47 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:33:47 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/ready$,/livez$,/metrics$,/health$,/healthz$) -INFO: 04:33:47 - uvicorn.error - Started server process [1] -INFO: 04:33:47 - uvicorn.error - Waiting for application startup. -INFO: 04:33:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:50 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:33:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:50 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:33:50 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:33:50 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash caff667a02b7f037838d32d34acfe0b0 -INFO: 04:33:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:33:50 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:33:50 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:33:50.424270629 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:33:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:33:50,645 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:50,646 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:33:50,698 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:50,698 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:33:50,749 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:50,750 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:33:50 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:33:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:33:53 - docling.document_converter - Going to convert document batch... -INFO: 04:33:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:33:53 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:33:53 - docling.document_converter - Finished converting document file in 0.65 sec. +INFO: 04:31:39 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:39 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:31:40 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:31:40 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:31:40 - docling_jobkit.connectors.plugins.defaults - Connector 'OpenSearchTargetProcessor' skipped — optional dependency not installed (No module named 'opensearchpy'). Install the matching extra to enable it. +INFO: 04:31:40 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:31:40 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:31:40 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/ready$,/metrics$,/healthz$,/health$) +INFO: 04:31:40 - uvicorn.error - Started server process [1] +INFO: 04:31:40 - uvicorn.error - Waiting for application startup. +INFO: 04:31:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:44 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:31:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:44 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:31:44 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:44 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash caff667a02b7f037838d32d34acfe0b0 +INFO: 04:31:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:31:44 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:31:44 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:31:44.762562130 [W:onnxruntime:Default, device_discovery.cc:134 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:31:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:31:45,153 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:45,155 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:31:45,327 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:45,327 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:31:45,381 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:45,381 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:31:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:48 - docling.document_converter - Going to convert document batch... +INFO: 04:31:48 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:31:48 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:48 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:632: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:33:53 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:33:53 - docling_jobkit.convert.results - Processed 1 docs in 0.72 seconds. -INFO: 04:33:53 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job def6a479-186e-45df-9da7-f8487ac6beff in 0.72 seconds -INFO: 04:33:53 - uvicorn.access - 172.17.0.1:34772 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:33:53 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:33:53 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:33:53 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:33:53 - docling_serve.app - [TENANT_ID] Task e0620f70-34da-4a90-973c-8b1b305b6daf created with tenant_id='default' -INFO: 04:33:53 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task e0620f70-34da-4a90-973c-8b1b305b6daf -INFO: 04:33:53 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:33:54 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash ab12ef348c8fc273bf2be7a49773b303 -INFO: 04:33:54 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:33:54 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:33:54,093 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:54,093 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:33:54,159 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:54,159 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:33:54,199 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:54,200 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:33:54 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:33:54 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:33:55 - docling.document_converter - Going to convert document batch... -INFO: 04:33:55 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:33:55 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:33:55 - docling.document_converter - Finished converting document file in 0.46 sec. +WARNING: 04:31:48 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:31:48 - docling_jobkit.convert.results - Processed 1 docs in 0.41 seconds. +INFO: 04:31:48 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job d2550ab8-4ce4-41c6-a4cb-3d8122ff8612 in 0.41 seconds +INFO: 04:31:49 - uvicorn.access - 172.17.0.1:54406 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:49 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:31:49 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:31:49 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:31:49 - docling_serve.app - [TENANT_ID] Task 2d2f4573-38d4-4c60-82c6-33aca6a3c67f created with tenant_id='default' +INFO: 04:31:49 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 2d2f4573-38d4-4c60-82c6-33aca6a3c67f +INFO: 04:31:49 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:49 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash ab12ef348c8fc273bf2be7a49773b303 +INFO: 04:31:49 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:31:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:31:49,542 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:49,542 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:31:49,585 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:49,585 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:31:49,643 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:49,643 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:31:49 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:50 - docling.document_converter - Going to convert document batch... +INFO: 04:31:50 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:31:50 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:50 - docling.document_converter - Finished converting document file in 0.33 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:632: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:33:55 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. -INFO: 04:33:55 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job e0620f70-34da-4a90-973c-8b1b305b6daf in 0.46 seconds -INFO: 04:33:55 - uvicorn.access - 172.17.0.1:34772 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:33:55 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:33:55 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:33:55 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:33:55 - docling_serve.app - [TENANT_ID] Task 30753b4b-b7a8-4f03-8dad-131cafa83e07 created with tenant_id='default' -INFO: 04:33:55 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 30753b4b-b7a8-4f03-8dad-131cafa83e07 -INFO: 04:33:55 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:33:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b3849eabdc7ecae5f3d54428a0162342 -INFO: 04:33:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:33:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:33:56,119 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:56,119 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:33:56,168 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:56,168 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:33:56,208 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:33:56,208 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:33:56 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:33:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:33:57 - docling.document_converter - Going to convert document batch... -INFO: 04:33:57 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:33:57 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:33:57 - docling.document_converter - Finished converting document file in 0.45 sec. +INFO: 04:31:50 - docling_jobkit.convert.results - Processed 1 docs in 0.33 seconds. +INFO: 04:31:50 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 2d2f4573-38d4-4c60-82c6-33aca6a3c67f in 0.33 seconds +INFO: 04:31:51 - uvicorn.access - 172.17.0.1:54406 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:51 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:31:51 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:31:51 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:31:51 - docling_serve.app - [TENANT_ID] Task eb6cccb8-4e56-434f-83aa-a25a112bfe89 created with tenant_id='default' +INFO: 04:31:51 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task eb6cccb8-4e56-434f-83aa-a25a112bfe89 +INFO: 04:31:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:31:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash b3849eabdc7ecae5f3d54428a0162342 +INFO: 04:31:51 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:31:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:31:51,546 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:51,546 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:31:51,587 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:51,587 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:31:51,658 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:31:51,658 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:31:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:31:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:31:52 - docling.document_converter - Going to convert document batch... +INFO: 04:31:52 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:31:52 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:31:52 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:632: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:33:57 - docling_jobkit.convert.results - Processed 1 docs in 0.49 seconds. -INFO: 04:33:57 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 30753b4b-b7a8-4f03-8dad-131cafa83e07 in 0.49 seconds -INFO: 04:33:57 - uvicorn.access - 172.17.0.1:34772 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:33:58 - uvicorn.access - 172.17.0.1:34772 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:33:58 - uvicorn.access - 172.17.0.1:34772 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:31:52 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 04:31:52 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job eb6cccb8-4e56-434f-83aa-a25a112bfe89 in 0.39 seconds +INFO: 04:31:53 - uvicorn.access - 172.17.0.1:54406 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:31:53 - uvicorn.access - 172.17.0.1:54406 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:31:53 - uvicorn.access - 172.17.0.1:54406 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2175,138 +2175,138 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:32:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:32:10 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:32:10 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:32:10 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' -INFO: 04:32:10 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:32:10 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:32:10 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/ready$,/livez$,/metrics$,/health$,/readyz$) -INFO: 04:32:10 - uvicorn.error - Started server process [1] -INFO: 04:32:10 - uvicorn.error - Waiting for application startup. -INFO: 04:32:13 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:32:13 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:32:13 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:32:13 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:32:13 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:32:13 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 -INFO: 04:32:13 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:32:13 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:32:13 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:32:13.515230245 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:32:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:32:13,737 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:13,738 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:32:13,801 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:13,802 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:32:13,866 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:13,866 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:32:13 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:32:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:32:16 - docling.document_converter - Going to convert document batch... -INFO: 04:32:16 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:32:16 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:32:17 - docling.document_converter - Finished converting document file in 0.73 sec. +INFO: 04:28:31 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:31 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:28:31 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:28:31 - docling_jobkit.connectors.connector_factory - Loading connector plugin 'docling_jobkit_defaults' +INFO: 04:28:31 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:28:31 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:28:31 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/ready$,/metrics$,/livez$,/healthz$,/health$) +INFO: 04:28:32 - uvicorn.error - Started server process [1] +INFO: 04:28:32 - uvicorn.error - Waiting for application startup. +INFO: 04:28:34 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:35 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:28:35 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:35 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:28:35 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 +INFO: 04:28:35 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:35 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:28:35 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:28:35.262487158 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:28:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:28:35,522 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:35,524 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:28:35,755 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:35,755 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:28:35,790 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:35,790 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:28:35 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:38 - docling.document_converter - Going to convert document batch... +INFO: 04:28:38 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:28:38 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:38 - docling.document_converter - Finished converting document file in 0.39 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:611: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:32:17 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:32:17 - docling_jobkit.convert.results - Processed 1 docs in 0.80 seconds. -INFO: 04:32:17 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e66a069f-5dcd-48c4-ac11-cdb0f5e1a06a in 0.80 seconds -INFO: 04:32:19 - uvicorn.access - 172.17.0.1:42048 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:32:19 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:32:19 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:32:19 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:32:19 - docling_serve.app - [TENANT_ID] Task 18d4f24f-7c75-4ed8-abd3-d81bba79ff8e created with tenant_id='default' -INFO: 04:32:19 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 18d4f24f-7c75-4ed8-abd3-d81bba79ff8e -INFO: 04:32:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:32:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 -INFO: 04:32:19 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:32:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:32:19,260 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:19,260 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:32:19,312 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:19,312 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:32:19,359 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:19,359 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:32:19 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:32:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:32:20 - docling.document_converter - Going to convert document batch... -INFO: 04:32:20 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:32:20 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:32:20 - docling.document_converter - Finished converting document file in 0.47 sec. +WARNING: 04:28:38 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:28:38 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 04:28:38 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c5a215e6-523d-4016-a107-6b486af50e39 in 0.43 seconds +INFO: 04:28:38 - uvicorn.access - 172.17.0.1:46320 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] Task 1e990ba0-269f-4087-9f4a-42b5a090647c created with tenant_id='default' +INFO: 04:28:38 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 1e990ba0-269f-4087-9f4a-42b5a090647c +INFO: 04:28:38 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:38 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 04:28:38 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:28:38 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:28:38,991 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:38,991 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:28:39,058 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:39,059 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:28:39,174 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:39,174 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:28:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:40 - docling.document_converter - Going to convert document batch... +INFO: 04:28:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:28:40 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:40 - docling.document_converter - Finished converting document file in 0.42 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:611: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:32:20 - docling_jobkit.convert.results - Processed 1 docs in 0.47 seconds. -INFO: 04:32:20 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 18d4f24f-7c75-4ed8-abd3-d81bba79ff8e in 0.47 seconds -INFO: 04:32:21 - uvicorn.access - 172.17.0.1:42048 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:32:21 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:32:21 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:32:21 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:32:21 - docling_serve.app - [TENANT_ID] Task ac4957cf-cf34-4c85-9a26-83f43baff985 created with tenant_id='default' -INFO: 04:32:21 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ac4957cf-cf34-4c85-9a26-83f43baff985 -INFO: 04:32:21 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:32:21 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc -INFO: 04:32:21 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:32:21 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:32:21,276 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:21,277 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:32:21,327 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:21,327 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:32:21,374 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:32:21,374 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:32:21 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:32:21 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:32:22 - docling.document_converter - Going to convert document batch... -INFO: 04:32:22 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:32:22 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:32:22 - docling.document_converter - Finished converting document file in 0.47 sec. +INFO: 04:28:40 - docling_jobkit.convert.results - Processed 1 docs in 0.42 seconds. +INFO: 04:28:40 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 1e990ba0-269f-4087-9f4a-42b5a090647c in 0.42 seconds +INFO: 04:28:40 - uvicorn.access - 172.17.0.1:46320 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:40 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:28:40 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:28:40 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:28:40 - docling_serve.app - [TENANT_ID] Task ccbcfb64-5b6a-4b21-a9a5-2d11bfb37560 created with tenant_id='default' +INFO: 04:28:40 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ccbcfb64-5b6a-4b21-a9a5-2d11bfb37560 +INFO: 04:28:40 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:40 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc +INFO: 04:28:40 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:28:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:28:41,008 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:41,008 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:28:41,071 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:41,072 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:28:41,107 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:41,107 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:28:41 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:42 - docling.document_converter - Going to convert document batch... +INFO: 04:28:42 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:28:42 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:42 - docling.document_converter - Finished converting document file in 0.37 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:611: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:32:22 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:32:22 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ac4957cf-cf34-4c85-9a26-83f43baff985 in 0.51 seconds -INFO: 04:32:23 - uvicorn.access - 172.17.0.1:42048 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:32:23 - uvicorn.access - 172.17.0.1:42048 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:32:23 - uvicorn.access - 172.17.0.1:42048 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:28:42 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 04:28:42 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ccbcfb64-5b6a-4b21-a9a5-2d11bfb37560 in 0.39 seconds +INFO: 04:28:42 - uvicorn.access - 172.17.0.1:46320 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:43 - uvicorn.access - 172.17.0.1:46320 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:28:43 - uvicorn.access - 172.17.0.1:46320 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2344,136 +2344,136 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:30:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:30:38 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:30:38 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:30:38 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:30:38 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/health$,/metrics$,/healthz$,/ready$,/livez$) -INFO: 04:30:38 - uvicorn.error - Started server process [1] -INFO: 04:30:38 - uvicorn.error - Waiting for application startup. -INFO: 04:30:41 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:30:41 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:30:41 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:30:41 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:30:41 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:30:41 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 -INFO: 04:30:41 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:30:41 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:30:41 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:30:41.688038585 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:30:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:30:41,905 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:41,906 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:30:41,964 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:41,965 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:30:42,011 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:42,011 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:30:42 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:30:42 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:30:45 - docling.document_converter - Going to convert document batch... -INFO: 04:30:45 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:30:45 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:30:45 - docling.document_converter - Finished converting document file in 0.75 sec. +INFO: 04:28:27 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:27 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:28:27 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:28:27 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:28:27 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/metrics$,/readyz$,/health$,/healthz$,/ready$) +INFO: 04:28:27 - uvicorn.error - Started server process [1] +INFO: 04:28:27 - uvicorn.error - Waiting for application startup. +INFO: 04:28:31 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:31 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:28:31 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:31 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:28:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:32 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 +INFO: 04:28:32 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:28:32 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:28:32 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:28:32.168735571 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:28:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:28:32,377 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:32,378 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:28:32,481 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:32,481 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:28:32,544 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:32,544 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:28:32 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:36 - docling.document_converter - Going to convert document batch... +INFO: 04:28:36 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:28:36 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:36 - docling.document_converter - Finished converting document file in 0.61 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:588: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:30:45 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:30:45 - docling_jobkit.convert.results - Processed 1 docs in 0.81 seconds. -INFO: 04:30:45 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 965b93c7-8d4d-4489-90d5-ba61061b45de in 0.81 seconds -INFO: 04:30:45 - uvicorn.access - 172.17.0.1:48972 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:30:45 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:30:45 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:30:45 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:30:45 - docling_serve.app - [TENANT_ID] Task 1c07fbd6-afe4-4f6b-868f-d8d0a37f5bce created with tenant_id='default' -INFO: 04:30:45 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 1c07fbd6-afe4-4f6b-868f-d8d0a37f5bce -INFO: 04:30:45 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:30:45 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 -INFO: 04:30:45 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:30:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:30:45,874 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:45,874 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:30:45,929 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:45,929 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:30:45,978 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:45,978 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:30:46 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:30:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:30:47 - docling.document_converter - Going to convert document batch... -INFO: 04:30:47 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:30:47 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:30:47 - docling.document_converter - Finished converting document file in 0.46 sec. +WARNING: 04:28:36 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:28:36 - docling_jobkit.convert.results - Processed 1 docs in 0.67 seconds. +INFO: 04:28:36 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b6439504-333d-48ea-8ab1-d34a0ddebf0a in 0.67 seconds +INFO: 04:28:36 - uvicorn.access - 172.17.0.1:51084 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:36 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:28:36 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:28:36 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:28:36 - docling_serve.app - [TENANT_ID] Task 991336af-2ca5-4e85-b262-3246828dd518 created with tenant_id='default' +INFO: 04:28:36 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 991336af-2ca5-4e85-b262-3246828dd518 +INFO: 04:28:36 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:36 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 04:28:36 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:28:36 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:28:37,009 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:37,010 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:28:37,101 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:37,102 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:28:37,173 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:37,174 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:28:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:38 - docling.document_converter - Going to convert document batch... +INFO: 04:28:38 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:28:38 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:38 - docling.document_converter - Finished converting document file in 0.33 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:588: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:30:47 - docling_jobkit.convert.results - Processed 1 docs in 0.47 seconds. -INFO: 04:30:47 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 1c07fbd6-afe4-4f6b-868f-d8d0a37f5bce in 0.47 seconds -INFO: 04:30:47 - uvicorn.access - 172.17.0.1:48972 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:30:47 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:30:47 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:30:47 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:30:47 - docling_serve.app - [TENANT_ID] Task afcacd05-e17d-41b4-91f9-7cf25437f3cd created with tenant_id='default' -INFO: 04:30:47 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task afcacd05-e17d-41b4-91f9-7cf25437f3cd -INFO: 04:30:47 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:30:47 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc -INFO: 04:30:47 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:30:47 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:30:47,895 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:47,895 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx -[INFO] 2026-11-09 04:30:47,959 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:47,959 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:30:48,005 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:30:48,005 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx -INFO: 04:30:48 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:30:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:30:48 - docling.document_converter - Going to convert document batch... -INFO: 04:30:48 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:30:48 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:30:49 - docling.document_converter - Finished converting document file in 0.34 sec. +INFO: 04:28:38 - docling_jobkit.convert.results - Processed 1 docs in 0.33 seconds. +INFO: 04:28:38 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 991336af-2ca5-4e85-b262-3246828dd518 in 0.33 seconds +INFO: 04:28:38 - uvicorn.access - 172.17.0.1:51084 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:28:38 - docling_serve.app - [TENANT_ID] Task 21cbdc90-cdfe-4a40-82c7-9b835c5c05ec created with tenant_id='default' +INFO: 04:28:38 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 21cbdc90-cdfe-4a40-82c7-9b835c5c05ec +INFO: 04:28:38 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:28:38 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc +INFO: 04:28:38 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:28:38 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:28:39,013 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:39,014 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-11-16 04:28:39,090 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:39,090 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:28:39,159 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:28:39,159 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 04:28:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:28:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:28:40 - docling.document_converter - Going to convert document batch... +INFO: 04:28:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:28:40 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:28:40 - docling.document_converter - Finished converting document file in 0.33 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:588: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:30:49 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. -INFO: 04:30:49 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job afcacd05-e17d-41b4-91f9-7cf25437f3cd in 0.37 seconds -INFO: 04:30:49 - uvicorn.access - 172.17.0.1:48972 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:30:50 - uvicorn.access - 172.17.0.1:48972 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:30:50 - uvicorn.access - 172.17.0.1:48972 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:28:40 - docling_jobkit.convert.results - Processed 1 docs in 0.35 seconds. +INFO: 04:28:40 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 21cbdc90-cdfe-4a40-82c7-9b835c5c05ec in 0.35 seconds +INFO: 04:28:40 - uvicorn.access - 172.17.0.1:51084 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:28:41 - uvicorn.access - 172.17.0.1:51084 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:28:41 - uvicorn.access - 172.17.0.1:51084 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2511,136 +2511,136 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:29:06 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:06 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:29:06 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:29:06 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:29:06 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/health$,/healthz$,/metrics$,/livez$,/ready$) -INFO: 04:29:06 - uvicorn.error - Started server process [1] -INFO: 04:29:06 - uvicorn.error - Waiting for application startup. -INFO: 04:29:09 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:10 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:29:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:10 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:29:10 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:29:10 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 -INFO: 04:29:10 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:29:10 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 04:29:10 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-11-09 04:29:10.137477435 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:29:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:29:10,573 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:10,574 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:29:10,667 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:10,667 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:29:10,714 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:10,714 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:29:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:29:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:29:13 - docling.document_converter - Going to convert document batch... -INFO: 04:29:13 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:29:13 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:29:13 - docling.document_converter - Finished converting document file in 0.65 sec. +INFO: 04:25:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:33 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:25:33 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:25:33 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:25:33 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/healthz$,/ready$,/readyz$,/health$) +INFO: 04:25:34 - uvicorn.error - Started server process [1] +INFO: 04:25:34 - uvicorn.error - Waiting for application startup. +INFO: 04:25:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:38 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:25:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:38 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:25:38 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:38 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 +INFO: 04:25:38 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:38 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 04:25:38 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-11-16 04:25:38.640643393 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:25:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:25:39,147 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:39,149 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:25:39,296 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:39,297 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:25:39,332 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:39,332 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:25:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:25:42 - docling.document_converter - Going to convert document batch... +INFO: 04:25:42 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:25:42 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:25:42 - docling.document_converter - Finished converting document file in 0.36 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:556: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -WARNING: 04:29:13 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:29:13 - docling_jobkit.convert.results - Processed 1 docs in 0.71 seconds. -INFO: 04:29:13 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8cc3f973-585e-4964-96cc-004200474250 in 0.71 seconds -INFO: 04:29:14 - uvicorn.access - 172.17.0.1:50714 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:29:14 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:29:14 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:29:14 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:29:14 - docling_serve.app - [TENANT_ID] Task 851c9a61-b288-43b3-916e-e60c8d7ab251 created with tenant_id='default' -INFO: 04:29:14 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 851c9a61-b288-43b3-916e-e60c8d7ab251 -INFO: 04:29:14 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:29:14 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac -INFO: 04:29:14 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:29:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:29:14,123 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:14,123 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:29:14,220 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:14,220 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:29:14,268 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:14,268 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:29:14 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:29:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:29:15 - docling.document_converter - Going to convert document batch... -INFO: 04:29:15 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:29:15 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:29:15 - docling.document_converter - Finished converting document file in 0.73 sec. +WARNING: 04:25:42 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:25:42 - docling_jobkit.convert.results - Processed 1 docs in 0.47 seconds. +INFO: 04:25:42 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job f8456495-4387-447d-aa71-534386f2c923 in 0.47 seconds +INFO: 04:25:43 - uvicorn.access - 172.17.0.1:46822 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:25:43 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:25:43 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:25:43 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:25:43 - docling_serve.app - [TENANT_ID] Task 04797477-a627-4200-8f84-6cd427a12929 created with tenant_id='default' +INFO: 04:25:43 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 04797477-a627-4200-8f84-6cd427a12929 +INFO: 04:25:43 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:43 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac +INFO: 04:25:43 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:25:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:25:43,280 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:43,280 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:25:43,384 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:43,384 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:25:43,434 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:43,434 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:25:43 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:25:44 - docling.document_converter - Going to convert document batch... +INFO: 04:25:44 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:25:44 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:25:44 - docling.document_converter - Finished converting document file in 0.55 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:556: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:29:15 - docling_jobkit.convert.results - Processed 1 docs in 0.73 seconds. -INFO: 04:29:15 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 851c9a61-b288-43b3-916e-e60c8d7ab251 in 0.73 seconds -INFO: 04:29:16 - uvicorn.access - 172.17.0.1:50714 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:29:16 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:29:16 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:29:16 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:29:16 - docling_serve.app - [TENANT_ID] Task e72614d3-f5f7-4ebe-8426-cfd2df015831 created with tenant_id='default' -INFO: 04:29:16 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e72614d3-f5f7-4ebe-8426-cfd2df015831 -INFO: 04:29:16 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:29:16 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 -INFO: 04:29:16 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 04:29:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:29:16,132 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:16,132 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:29:16,219 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:16,220 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:29:16,268 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:29:16,268 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:29:16 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:29:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:29:17 - docling.document_converter - Going to convert document batch... -INFO: 04:29:17 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:29:17 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:29:17 - docling.document_converter - Finished converting document file in 0.33 sec. +INFO: 04:25:44 - docling_jobkit.convert.results - Processed 1 docs in 0.55 seconds. +INFO: 04:25:44 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 04797477-a627-4200-8f84-6cd427a12929 in 0.55 seconds +INFO: 04:25:45 - uvicorn.access - 172.17.0.1:46822 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:25:45 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:25:45 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:25:45 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:25:45 - docling_serve.app - [TENANT_ID] Task a3326469-bf49-411e-b6be-a456f7b325ef created with tenant_id='default' +INFO: 04:25:45 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task a3326469-bf49-411e-b6be-a456f7b325ef +INFO: 04:25:45 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:45 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 +INFO: 04:25:45 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 04:25:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:25:45,282 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:45,282 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:25:45,364 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:45,364 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:25:45,419 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:45,419 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:25:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:25:46 - docling.document_converter - Going to convert document batch... +INFO: 04:25:46 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:25:46 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:25:46 - docling.document_converter - Finished converting document file in 0.32 sec. /opt/app-root/lib64/python3.12/site-packages/docling/datamodel/base_models.py:556: RuntimeWarning: Mean of empty slice np.nanmean( /opt/app-root/lib64/python3.12/site-packages/numpy/lib/_nanfunctions_impl.py:1573: RuntimeWarning: All-NaN slice encountered return _nanquantile_unchecked( -INFO: 04:29:17 - docling_jobkit.convert.results - Processed 1 docs in 0.37 seconds. -INFO: 04:29:17 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e72614d3-f5f7-4ebe-8426-cfd2df015831 in 0.37 seconds -INFO: 04:29:18 - uvicorn.access - 172.17.0.1:50714 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:29:18 - uvicorn.access - 172.17.0.1:50714 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:29:18 - uvicorn.access - 172.17.0.1:50714 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:25:46 - docling_jobkit.convert.results - Processed 1 docs in 0.34 seconds. +INFO: 04:25:46 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job a3326469-bf49-411e-b6be-a456f7b325ef in 0.34 seconds +INFO: 04:25:47 - uvicorn.access - 172.17.0.1:46822 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:25:47 - uvicorn.access - 172.17.0.1:46822 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:25:47 - uvicorn.access - 172.17.0.1:46822 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2678,120 +2678,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:27:30 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:27:30 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:27:30 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:27:30 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:27:30 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/metrics$,/healthz$,/health$,/ready$) -INFO: 04:27:30 - uvicorn.error - Started server process [1] -INFO: 04:27:30 - uvicorn.error - Waiting for application startup. -INFO: 04:27:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:27:33 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:27:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:27:33 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:27:33 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:27:33 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e -INFO: 04:27:33 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:27:33 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-11-09 04:27:33.803461752 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:27:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:27:34,071 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:34,072 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:27:34,161 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:34,161 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:27:34,206 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:34,207 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:27:34 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:27:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:27:36 - docling.document_converter - Going to convert document batch... -INFO: 04:27:36 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:27:36 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:27:36 - docling.document_converter - Finished converting document file in 0.75 sec. -WARNING: 04:27:36 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:27:36 - docling_jobkit.convert.results - Processed 1 docs in 0.81 seconds. -INFO: 04:27:36 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 3c1b79e1-e88c-46de-a669-27de12469b5d in 0.81 seconds -INFO: 04:27:37 - uvicorn.access - 172.17.0.1:37780 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:27:37 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:27:37 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:27:37 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:27:37 - docling_serve.app - [TENANT_ID] Task 0223f7ee-ef1c-40a7-8f58-feeaffd86ed0 created with tenant_id='default' -INFO: 04:27:37 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 0223f7ee-ef1c-40a7-8f58-feeaffd86ed0 -INFO: 04:27:37 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:27:37 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a -INFO: 04:27:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:27:37,293 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:37,293 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:27:37,384 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:37,385 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:27:37,431 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:37,431 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:27:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:27:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:27:38 - docling.document_converter - Going to convert document batch... -INFO: 04:27:38 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:27:38 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:27:38 - docling.document_converter - Finished converting document file in 0.48 sec. -INFO: 04:27:38 - docling_jobkit.convert.results - Processed 1 docs in 0.48 seconds. -INFO: 04:27:38 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 0223f7ee-ef1c-40a7-8f58-feeaffd86ed0 in 0.48 seconds -INFO: 04:27:39 - uvicorn.access - 172.17.0.1:37780 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:27:39 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:27:39 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:27:39 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:27:39 - docling_serve.app - [TENANT_ID] Task 08e1860d-c01a-4919-b61b-6258a15a1ddf created with tenant_id='default' -INFO: 04:27:39 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 08e1860d-c01a-4919-b61b-6258a15a1ddf -INFO: 04:27:39 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:27:39 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 -INFO: 04:27:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:27:39,307 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:39,308 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:27:39,393 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:39,394 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:27:39,440 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:27:39,440 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:27:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:27:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:27:40 - docling.document_converter - Going to convert document batch... -INFO: 04:27:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:27:40 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:27:40 - docling.document_converter - Finished converting document file in 0.48 sec. -INFO: 04:27:40 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:27:40 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 08e1860d-c01a-4919-b61b-6258a15a1ddf in 0.51 seconds -INFO: 04:27:41 - uvicorn.access - 172.17.0.1:37780 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:27:41 - uvicorn.access - 172.17.0.1:37780 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:27:41 - uvicorn.access - 172.17.0.1:37780 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:25:29 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:29 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:25:29 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:25:29 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:25:29 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/healthz$,/health$,/readyz$,/ready$) +INFO: 04:25:29 - uvicorn.error - Started server process [1] +INFO: 04:25:29 - uvicorn.error - Waiting for application startup. +INFO: 04:25:34 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:34 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:25:34 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:34 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:25:34 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e +INFO: 04:25:35 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:25:35 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-11-16 04:25:35.196427844 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:25:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:25:35,500 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:35,502 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:25:35,632 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:35,633 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:25:35,687 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:35,687 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:25:35 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:25:38 - docling.document_converter - Going to convert document batch... +INFO: 04:25:38 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:25:38 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:25:38 - docling.document_converter - Finished converting document file in 0.37 sec. +WARNING: 04:25:38 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:25:38 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 04:25:38 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e36150f2-a5f1-4ac1-a335-a76e9a48724a in 0.43 seconds +INFO: 04:25:39 - uvicorn.access - 172.17.0.1:45658 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:25:39 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:25:39 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:25:39 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:25:39 - docling_serve.app - [TENANT_ID] Task 095d51ee-104c-46a8-9b2f-c1a38c3d070b created with tenant_id='default' +INFO: 04:25:39 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 095d51ee-104c-46a8-9b2f-c1a38c3d070b +INFO: 04:25:39 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:39 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a +INFO: 04:25:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:25:39,634 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:39,634 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:25:39,731 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:39,731 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:25:39,768 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:39,768 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:25:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:25:40 - docling.document_converter - Going to convert document batch... +INFO: 04:25:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:25:40 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:25:40 - docling.document_converter - Finished converting document file in 0.34 sec. +INFO: 04:25:40 - docling_jobkit.convert.results - Processed 1 docs in 0.34 seconds. +INFO: 04:25:40 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 095d51ee-104c-46a8-9b2f-c1a38c3d070b in 0.34 seconds +INFO: 04:25:41 - uvicorn.access - 172.17.0.1:45658 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:25:41 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:25:41 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:25:41 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:25:41 - docling_serve.app - [TENANT_ID] Task 7bb69abb-73b0-43e5-a277-a707fba55a5a created with tenant_id='default' +INFO: 04:25:41 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 7bb69abb-73b0-43e5-a277-a707fba55a5a +INFO: 04:25:41 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:25:41 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 +INFO: 04:25:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:25:41,287 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:41,287 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:25:41,397 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:41,397 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:25:41,496 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:25:41,496 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:25:41 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:25:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:25:42 - docling.document_converter - Going to convert document batch... +INFO: 04:25:42 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:25:42 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:25:42 - docling.document_converter - Finished converting document file in 0.36 sec. +INFO: 04:25:42 - docling_jobkit.convert.results - Processed 1 docs in 0.39 seconds. +INFO: 04:25:42 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 7bb69abb-73b0-43e5-a277-a707fba55a5a in 0.39 seconds +INFO: 04:25:43 - uvicorn.access - 172.17.0.1:45658 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:25:43 - uvicorn.access - 172.17.0.1:45658 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:25:43 - uvicorn.access - 172.17.0.1:45658 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2829,120 +2829,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:26:02 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:26:02 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:26:02 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:26:02 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:26:02 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/health$,/livez$,/ready$,/healthz$,/readyz$) -INFO: 04:26:02 - uvicorn.error - Started server process [1] -INFO: 04:26:02 - uvicorn.error - Waiting for application startup. -INFO: 04:26:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:26:05 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:26:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:26:05 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:26:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:26:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 04:26:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:26:05 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-11-09 04:26:05.400710714 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:26:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:26:05,661 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:05,662 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:26:05,763 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:05,763 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:26:05,809 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:05,809 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:26:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:26:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:26:08 - docling.document_converter - Going to convert document batch... -INFO: 04:26:08 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:26:08 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:26:08 - docling.document_converter - Finished converting document file in 0.71 sec. -WARNING: 04:26:08 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:26:08 - docling_jobkit.convert.results - Processed 1 docs in 0.77 seconds. -INFO: 04:26:08 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 1e89ad8b-5e08-4e0d-a946-2c44ac73ed2e in 0.77 seconds -INFO: 04:26:08 - uvicorn.access - 172.17.0.1:44980 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:26:08 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:26:08 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:26:08 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:26:08 - docling_serve.app - [TENANT_ID] Task ad043534-3fd0-434d-83bd-d93169d0fdc2 created with tenant_id='default' -INFO: 04:26:08 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task ad043534-3fd0-434d-83bd-d93169d0fdc2 -INFO: 04:26:08 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:26:08 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 04:26:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:26:08,817 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:08,817 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:26:08,913 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:08,913 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:26:08,959 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:08,959 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:26:09 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:26:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:26:10 - docling.document_converter - Going to convert document batch... -INFO: 04:26:10 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:26:10 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:26:10 - docling.document_converter - Finished converting document file in 0.45 sec. -INFO: 04:26:10 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. -INFO: 04:26:10 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job ad043534-3fd0-434d-83bd-d93169d0fdc2 in 0.45 seconds -INFO: 04:26:10 - uvicorn.access - 172.17.0.1:44980 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:26:10 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:26:10 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:26:10 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:26:10 - docling_serve.app - [TENANT_ID] Task 76880d3e-f78d-4fb5-bb4e-03716c648ec1 created with tenant_id='default' -INFO: 04:26:10 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 76880d3e-f78d-4fb5-bb4e-03716c648ec1 -INFO: 04:26:10 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:26:10 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 04:26:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:26:10,835 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:10,835 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:26:10,921 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:10,921 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:26:10,968 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:26:10,968 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:26:11 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:26:11 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:26:12 - docling.document_converter - Going to convert document batch... -INFO: 04:26:12 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:26:12 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:26:12 - docling.document_converter - Finished converting document file in 0.54 sec. -INFO: 04:26:12 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. -INFO: 04:26:12 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 76880d3e-f78d-4fb5-bb4e-03716c648ec1 in 0.58 seconds -INFO: 04:26:12 - uvicorn.access - 172.17.0.1:44980 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:26:13 - uvicorn.access - 172.17.0.1:44980 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:26:13 - uvicorn.access - 172.17.0.1:44980 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:22:31 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:31 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:22:31 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:22:31 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:22:31 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/healthz$,/metrics$,/readyz$,/health$,/ready$) +INFO: 04:22:31 - uvicorn.error - Started server process [1] +INFO: 04:22:31 - uvicorn.error - Waiting for application startup. +INFO: 04:22:35 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:35 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:22:35 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:35 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:22:35 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:22:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 04:22:35 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:35 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-11-16 04:22:35.750984100 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:22:36 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:22:36,182 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:36,183 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:22:36,317 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:36,317 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:22:36,353 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:36,353 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:22:36 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:22:36 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:22:38 - docling.document_converter - Going to convert document batch... +INFO: 04:22:38 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:22:38 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:22:38 - docling.document_converter - Finished converting document file in 0.36 sec. +WARNING: 04:22:38 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:22:38 - docling_jobkit.convert.results - Processed 1 docs in 0.40 seconds. +INFO: 04:22:38 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job dc0af1c0-e4b6-419c-83c3-5b865fd19496 in 0.40 seconds +INFO: 04:22:39 - uvicorn.access - 172.17.0.1:53124 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:22:39 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:22:39 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:22:39 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:22:39 - docling_serve.app - [TENANT_ID] Task f052f6b8-9599-4140-b5bc-190fab3056bd created with tenant_id='default' +INFO: 04:22:39 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task f052f6b8-9599-4140-b5bc-190fab3056bd +INFO: 04:22:39 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:22:39 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 04:22:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:22:39,345 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:39,345 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:22:39,426 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:39,426 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:22:39,461 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:39,461 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:22:39 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:22:39 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:22:40 - docling.document_converter - Going to convert document batch... +INFO: 04:22:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:22:40 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:22:40 - docling.document_converter - Finished converting document file in 0.32 sec. +INFO: 04:22:40 - docling_jobkit.convert.results - Processed 1 docs in 0.32 seconds. +INFO: 04:22:40 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job f052f6b8-9599-4140-b5bc-190fab3056bd in 0.32 seconds +INFO: 04:22:41 - uvicorn.access - 172.17.0.1:53124 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:22:41 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:22:41 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:22:41 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:22:41 - docling_serve.app - [TENANT_ID] Task b035d79e-14a1-4823-805f-d3ecf0590ef0 created with tenant_id='default' +INFO: 04:22:41 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task b035d79e-14a1-4823-805f-d3ecf0590ef0 +INFO: 04:22:41 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:22:41 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 04:22:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:22:41,360 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:41,360 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:22:41,463 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:41,463 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:22:41,498 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:41,498 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:22:41 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:22:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:22:42 - docling.document_converter - Going to convert document batch... +INFO: 04:22:42 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:22:42 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:22:42 - docling.document_converter - Finished converting document file in 0.24 sec. +INFO: 04:22:42 - docling_jobkit.convert.results - Processed 1 docs in 0.26 seconds. +INFO: 04:22:42 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job b035d79e-14a1-4823-805f-d3ecf0590ef0 in 0.26 seconds +INFO: 04:22:43 - uvicorn.access - 172.17.0.1:53124 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:22:43 - uvicorn.access - 172.17.0.1:53124 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:22:43 - uvicorn.access - 172.17.0.1:53124 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -2980,120 +2980,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:24:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:24:25 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:24:25 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:24:25 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:24:25 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/ready$,/livez$,/metrics$,/healthz$,/readyz$) -INFO: 04:24:25 - uvicorn.error - Started server process [1] -INFO: 04:24:25 - uvicorn.error - Waiting for application startup. -INFO: 04:24:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:24:28 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:24:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:24:28 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:24:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:24:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 04:24:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:24:28 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-11-09 04:24:28.902469245 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:24:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:24:29,164 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:29,166 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:24:29,257 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:29,257 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:24:29,302 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:29,302 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:24:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:24:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:24:32 - docling.document_converter - Going to convert document batch... -INFO: 04:24:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:24:32 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:24:32 - docling.document_converter - Finished converting document file in 0.72 sec. -WARNING: 04:24:32 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:24:32 - docling_jobkit.convert.results - Processed 1 docs in 0.78 seconds. -INFO: 04:24:32 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 33cf66ad-3950-4f6c-8ac4-6d494c3ee474 in 0.78 seconds -INFO: 04:24:33 - uvicorn.access - 172.17.0.1:55460 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:24:33 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:24:33 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:24:33 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:24:33 - docling_serve.app - [TENANT_ID] Task f57aa566-7a6d-4cc8-95bb-3b96a65820bb created with tenant_id='default' -INFO: 04:24:33 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task f57aa566-7a6d-4cc8-95bb-3b96a65820bb -INFO: 04:24:33 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:24:33 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 04:24:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:24:33,124 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:33,124 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:24:33,236 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:33,237 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:24:33,283 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:33,283 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:24:33 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:24:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:24:34 - docling.document_converter - Going to convert document batch... -INFO: 04:24:34 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:24:34 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:24:34 - docling.document_converter - Finished converting document file in 0.44 sec. -INFO: 04:24:34 - docling_jobkit.convert.results - Processed 1 docs in 0.44 seconds. -INFO: 04:24:34 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job f57aa566-7a6d-4cc8-95bb-3b96a65820bb in 0.44 seconds -INFO: 04:24:35 - uvicorn.access - 172.17.0.1:55460 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:24:35 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:24:35 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:24:35 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:24:35 - docling_serve.app - [TENANT_ID] Task 3b350e46-ca5c-418a-afda-901a3197d005 created with tenant_id='default' -INFO: 04:24:35 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 3b350e46-ca5c-418a-afda-901a3197d005 -INFO: 04:24:35 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:24:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 04:24:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:24:35,150 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:35,150 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:24:35,244 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:35,244 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:24:35,292 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:24:35,293 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:24:35 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:24:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:24:36 - docling.document_converter - Going to convert document batch... -INFO: 04:24:36 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:24:36 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:24:36 - docling.document_converter - Finished converting document file in 0.60 sec. -INFO: 04:24:36 - docling_jobkit.convert.results - Processed 1 docs in 0.63 seconds. -INFO: 04:24:36 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 3b350e46-ca5c-418a-afda-901a3197d005 in 0.63 seconds -INFO: 04:24:37 - uvicorn.access - 172.17.0.1:55460 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:24:37 - uvicorn.access - 172.17.0.1:55460 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:24:37 - uvicorn.access - 172.17.0.1:55460 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:22:17 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:18 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:22:18 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:22:18 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:22:18 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/metrics$,/livez$,/health$,/readyz$,/ready$) +INFO: 04:22:18 - uvicorn.error - Started server process [1] +INFO: 04:22:18 - uvicorn.error - Waiting for application startup. +INFO: 04:22:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:25 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:22:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:25 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:22:25 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:22:25 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 04:22:25 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:22:25 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-11-16 04:22:25.480844388 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:22:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:22:25,896 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:25,898 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:22:26,029 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:26,029 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:22:26,066 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:26,066 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:22:26 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:22:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:22:28 - docling.document_converter - Going to convert document batch... +INFO: 04:22:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:22:28 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:22:28 - docling.document_converter - Finished converting document file in 0.45 sec. +WARNING: 04:22:28 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:22:28 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. +INFO: 04:22:28 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job a8471142-752f-4310-beee-42635cd72882 in 0.50 seconds +INFO: 04:22:29 - uvicorn.access - 172.17.0.1:36356 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:22:29 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:22:29 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:22:29 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:22:29 - docling_serve.app - [TENANT_ID] Task 7b6fb5d3-10b9-4682-aee0-fa7e234c0e94 created with tenant_id='default' +INFO: 04:22:29 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 7b6fb5d3-10b9-4682-aee0-fa7e234c0e94 +INFO: 04:22:29 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:22:29 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 04:22:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:22:29,348 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:29,348 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:22:29,431 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:29,431 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:22:29,465 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:29,466 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:22:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:22:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:22:30 - docling.document_converter - Going to convert document batch... +INFO: 04:22:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:22:30 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:22:30 - docling.document_converter - Finished converting document file in 0.36 sec. +INFO: 04:22:30 - docling_jobkit.convert.results - Processed 1 docs in 0.36 seconds. +INFO: 04:22:30 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 7b6fb5d3-10b9-4682-aee0-fa7e234c0e94 in 0.36 seconds +INFO: 04:22:31 - uvicorn.access - 172.17.0.1:36356 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:22:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:22:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:22:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:22:31 - docling_serve.app - [TENANT_ID] Task c1267578-2c66-4178-927d-bd188aa0880c created with tenant_id='default' +INFO: 04:22:31 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task c1267578-2c66-4178-927d-bd188aa0880c +INFO: 04:22:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:22:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 04:22:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:22:31,338 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:31,338 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:22:31,426 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:31,426 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:22:31,476 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:22:31,476 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:22:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:22:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:22:32 - docling.document_converter - Going to convert document batch... +INFO: 04:22:32 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:22:32 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:22:32 - docling.document_converter - Finished converting document file in 0.42 sec. +INFO: 04:22:32 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. +INFO: 04:22:32 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c1267578-2c66-4178-927d-bd188aa0880c in 0.45 seconds +INFO: 04:22:33 - uvicorn.access - 172.17.0.1:36356 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:22:33 - uvicorn.access - 172.17.0.1:36356 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:22:33 - uvicorn.access - 172.17.0.1:36356 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -3131,120 +3131,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:23:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:23:05 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:23:05 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:23:05 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:23:05 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/metrics$,/livez$,/ready$,/health$,/readyz$) -INFO: 04:23:05 - uvicorn.error - Started server process [1] -INFO: 04:23:05 - uvicorn.error - Waiting for application startup. -INFO: 04:23:08 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:23:08 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:23:08 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:23:08 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:23:08 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:23:08 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 04:23:08 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:23:08 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-11-09 04:23:08.505219282 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:23:08 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:23:08,814 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:08,816 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:23:08,915 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:08,915 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:23:08,961 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:08,961 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:23:09 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:23:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:23:11 - docling.document_converter - Going to convert document batch... -INFO: 04:23:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:23:11 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:23:11 - docling.document_converter - Finished converting document file in 0.48 sec. -WARNING: 04:23:12 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:23:12 - docling_jobkit.convert.results - Processed 1 docs in 0.79 seconds. -INFO: 04:23:12 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 5d0b9053-6083-453b-8f14-02e3824bdba2 in 0.79 seconds -INFO: 04:23:12 - uvicorn.access - 172.17.0.1:38738 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:23:12 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:23:12 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:23:12 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:23:12 - docling_serve.app - [TENANT_ID] Task cc641165-c79b-43e0-a5c9-63aeec62527b created with tenant_id='default' -INFO: 04:23:12 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task cc641165-c79b-43e0-a5c9-63aeec62527b -INFO: 04:23:12 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:23:12 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 -INFO: 04:23:12 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:23:12,608 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:12,609 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:23:12,696 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:12,696 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:23:12,742 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:12,742 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:23:12 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:23:12 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:23:13 - docling.document_converter - Going to convert document batch... -INFO: 04:23:13 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:23:13 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:23:13 - docling.document_converter - Finished converting document file in 0.45 sec. -INFO: 04:23:13 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. -INFO: 04:23:13 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job cc641165-c79b-43e0-a5c9-63aeec62527b in 0.46 seconds -INFO: 04:23:14 - uvicorn.access - 172.17.0.1:38738 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:23:14 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:23:14 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:23:14 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:23:14 - docling_serve.app - [TENANT_ID] Task e3c342be-e39b-4a58-bf4f-48955f7e7948 created with tenant_id='default' -INFO: 04:23:14 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e3c342be-e39b-4a58-bf4f-48955f7e7948 -INFO: 04:23:14 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:23:14 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 -INFO: 04:23:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:23:14,622 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:14,622 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:23:14,710 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:14,711 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:23:14,757 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:23:14,758 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:23:14 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:23:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:23:15 - docling.document_converter - Going to convert document batch... -INFO: 04:23:15 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:23:15 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:23:15 - docling.document_converter - Finished converting document file in 0.47 sec. -INFO: 04:23:16 - docling_jobkit.convert.results - Processed 1 docs in 0.51 seconds. -INFO: 04:23:16 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e3c342be-e39b-4a58-bf4f-48955f7e7948 in 0.51 seconds -INFO: 04:23:16 - uvicorn.access - 172.17.0.1:38738 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:23:16 - uvicorn.access - 172.17.0.1:38738 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:23:16 - uvicorn.access - 172.17.0.1:38738 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:19:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:24 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:19:24 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:19:24 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:19:24 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/readyz$,/livez$,/ready$,/healthz$,/health$) +INFO: 04:19:24 - uvicorn.error - Started server process [1] +INFO: 04:19:24 - uvicorn.error - Waiting for application startup. +INFO: 04:19:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:28 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:19:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:28 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:19:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 04:19:28 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:28 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-11-16 04:19:28.221243623 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:19:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:19:28,725 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:28,726 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:19:28,882 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:28,883 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:19:28,925 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:28,925 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:31 - docling.document_converter - Going to convert document batch... +INFO: 04:19:31 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:31 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:31 - docling.document_converter - Finished converting document file in 0.26 sec. +WARNING: 04:19:31 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:19:31 - docling_jobkit.convert.results - Processed 1 docs in 0.65 seconds. +INFO: 04:19:31 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 208bf2dc-79fe-45fc-b463-92323cd96b3e in 0.65 seconds +INFO: 04:19:32 - uvicorn.access - 172.17.0.1:53520 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:32 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:19:32 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:19:32 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:19:32 - docling_serve.app - [TENANT_ID] Task d6bb61eb-8eec-4082-89a3-c1551badb58c created with tenant_id='default' +INFO: 04:19:32 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task d6bb61eb-8eec-4082-89a3-c1551badb58c +INFO: 04:19:32 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:32 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 +INFO: 04:19:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:19:32,356 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:32,356 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:19:32,436 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:32,436 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:19:32,471 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:32,472 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:32 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:32 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:33 - docling.document_converter - Going to convert document batch... +INFO: 04:19:33 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:33 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:33 - docling.document_converter - Finished converting document file in 0.43 sec. +INFO: 04:19:33 - docling_jobkit.convert.results - Processed 1 docs in 0.44 seconds. +INFO: 04:19:33 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job d6bb61eb-8eec-4082-89a3-c1551badb58c in 0.44 seconds +INFO: 04:19:34 - uvicorn.access - 172.17.0.1:53520 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:34 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:19:34 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:19:34 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:19:34 - docling_serve.app - [TENANT_ID] Task 2ca62cd2-8175-40dd-aece-16276edfc8d3 created with tenant_id='default' +INFO: 04:19:34 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 2ca62cd2-8175-40dd-aece-16276edfc8d3 +INFO: 04:19:34 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:34 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 +INFO: 04:19:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:19:34,366 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:34,366 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:19:34,459 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:34,459 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:19:34,501 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:34,501 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:34 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:34 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:35 - docling.document_converter - Going to convert document batch... +INFO: 04:19:35 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:35 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:35 - docling.document_converter - Finished converting document file in 0.33 sec. +INFO: 04:19:35 - docling_jobkit.convert.results - Processed 1 docs in 0.36 seconds. +INFO: 04:19:35 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2ca62cd2-8175-40dd-aece-16276edfc8d3 in 0.36 seconds +INFO: 04:19:36 - uvicorn.access - 172.17.0.1:53520 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:36 - uvicorn.access - 172.17.0.1:53520 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:19:36 - uvicorn.access - 172.17.0.1:53520 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -3282,120 +3282,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 04:21:34 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:21:34 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 04:21:34 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 04:21:34 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 04:21:34 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/metrics$,/readyz$,/ready$,/livez$) -INFO: 04:21:34 - uvicorn.error - Started server process [1] -INFO: 04:21:34 - uvicorn.error - Waiting for application startup. -INFO: 04:21:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:21:37 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 04:21:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:21:37 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 04:21:37 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:21:37 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf -INFO: 04:21:37 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 04:21:37 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-11-09 04:21:37.304276284 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -INFO: 04:21:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:21:37,569 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:37,570 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:21:37,659 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:37,659 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:21:37,705 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:37,705 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:21:37 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:21:37 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:21:40 - docling.document_converter - Going to convert document batch... -INFO: 04:21:40 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:21:40 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:21:40 - docling.document_converter - Finished converting document file in 0.49 sec. -WARNING: 04:21:41 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 04:21:41 - docling_jobkit.convert.results - Processed 1 docs in 0.80 seconds. -INFO: 04:21:41 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 432e9413-00ee-4edc-b5ec-865eb04ae8e1 in 0.80 seconds -INFO: 04:21:41 - uvicorn.access - 172.17.0.1:33482 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:21:41 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:21:41 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:21:41 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:21:41 - docling_serve.app - [TENANT_ID] Task 3855e080-5435-451d-953e-8a5350038d9a created with tenant_id='default' -INFO: 04:21:41 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 3855e080-5435-451d-953e-8a5350038d9a -INFO: 04:21:41 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:21:41 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b -INFO: 04:21:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:21:41,407 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:41,407 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:21:41,498 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:41,498 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:21:41,544 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:41,544 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:21:41 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:21:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:21:42 - docling.document_converter - Going to convert document batch... -INFO: 04:21:42 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:21:42 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:21:42 - docling.document_converter - Finished converting document file in 0.33 sec. -INFO: 04:21:42 - docling_jobkit.convert.results - Processed 1 docs in 0.34 seconds. -INFO: 04:21:42 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 3855e080-5435-451d-953e-8a5350038d9a in 0.34 seconds -INFO: 04:21:43 - uvicorn.access - 172.17.0.1:33482 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:21:43 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 04:21:43 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 04:21:43 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 04:21:43 - docling_serve.app - [TENANT_ID] Task 870dbe25-447e-4a57-a8a7-416ea09d4991 created with tenant_id='default' -INFO: 04:21:43 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 870dbe25-447e-4a57-a8a7-416ea09d4991 -INFO: 04:21:43 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 04:21:43 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb -INFO: 04:21:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-11-09 04:21:43,411 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:43,411 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:21:43,498 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:43,498 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:21:43,545 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:21:43,545 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 04:21:43 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 04:21:43 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 04:21:44 - docling.document_converter - Going to convert document batch... -INFO: 04:21:44 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 04:21:44 - docling.pipeline.base_pipeline - Processing document file -INFO: 04:21:44 - docling.document_converter - Finished converting document file in 0.45 sec. -INFO: 04:21:44 - docling_jobkit.convert.results - Processed 1 docs in 0.49 seconds. -INFO: 04:21:44 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 870dbe25-447e-4a57-a8a7-416ea09d4991 in 0.49 seconds -INFO: 04:21:45 - uvicorn.access - 172.17.0.1:33482 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 04:21:45 - uvicorn.access - 172.17.0.1:33482 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 04:21:45 - uvicorn.access - 172.17.0.1:33482 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 04:19:17 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:17 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 04:19:17 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 04:19:17 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 04:19:17 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/readyz$,/metrics$,/livez$,/health$,/ready$) +INFO: 04:19:17 - uvicorn.error - Started server process [1] +INFO: 04:19:17 - uvicorn.error - Waiting for application startup. +INFO: 04:19:21 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:21 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 04:19:21 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:21 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 04:19:21 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:21 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf +INFO: 04:19:21 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 04:19:21 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-11-16 04:19:21.888853744 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ +INFO: 04:19:22 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:19:22,280 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:22,324 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:19:22,493 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:22,494 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:19:22,549 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:22,550 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:22 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:22 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:25 - docling.document_converter - Going to convert document batch... +INFO: 04:19:25 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:25 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:25 - docling.document_converter - Finished converting document file in 0.41 sec. +WARNING: 04:19:25 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 04:19:25 - docling_jobkit.convert.results - Processed 1 docs in 0.78 seconds. +INFO: 04:19:25 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 559f2669-1cce-429c-9cda-b75a8bba2d19 in 0.78 seconds +INFO: 04:19:26 - uvicorn.access - 172.17.0.1:35042 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:26 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:19:26 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:19:26 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:19:26 - docling_serve.app - [TENANT_ID] Task 2f1a46e7-2e3e-438a-8ce5-077524d7df90 created with tenant_id='default' +INFO: 04:19:26 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 2f1a46e7-2e3e-438a-8ce5-077524d7df90 +INFO: 04:19:26 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:26 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b +INFO: 04:19:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:19:26,332 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:26,332 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:19:26,422 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:26,422 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:19:26,458 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:26,458 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:26 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:26 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:27 - docling.document_converter - Going to convert document batch... +INFO: 04:19:27 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:27 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:27 - docling.document_converter - Finished converting document file in 0.45 sec. +INFO: 04:19:27 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 04:19:27 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 2f1a46e7-2e3e-438a-8ce5-077524d7df90 in 0.46 seconds +INFO: 04:19:28 - uvicorn.access - 172.17.0.1:35042 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:28 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 04:19:28 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 04:19:28 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 04:19:28 - docling_serve.app - [TENANT_ID] Task 6099274f-cff5-41b5-a264-8ccaf5ed760a created with tenant_id='default' +INFO: 04:19:28 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 6099274f-cff5-41b5-a264-8ccaf5ed760a +INFO: 04:19:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 04:19:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb +INFO: 04:19:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-11-16 04:19:28,337 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:28,337 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-11-16 04:19:28,440 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:28,440 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx +[INFO] 2026-11-16 04:19:28,493 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-11-16 04:19:28,493 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 04:19:28 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 04:19:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 04:19:29 - docling.document_converter - Going to convert document batch... +INFO: 04:19:29 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 04:19:29 - docling.pipeline.base_pipeline - Processing document file +INFO: 04:19:29 - docling.document_converter - Finished converting document file in 0.27 sec. +INFO: 04:19:29 - docling_jobkit.convert.results - Processed 1 docs in 0.30 seconds. +INFO: 04:19:29 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 6099274f-cff5-41b5-a264-8ccaf5ed760a in 0.30 seconds +INFO: 04:19:30 - uvicorn.access - 172.17.0.1:35042 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 04:19:30 - uvicorn.access - 172.17.0.1:35042 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 04:19:30 - uvicorn.access - 172.17.0.1:35042 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -3433,37 +3433,37 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -2026-11-09 04:20:02.636294730 [W:onnxruntime:Default, device_discovery.cc:133 GetPciBusId] Skipping pci_bus_id for PCI path at "/sys/devices/LNXSYSTM:00/LNXSYBUS:00/ACPI0004:00/MSFT1000:00/5620e0c7-8062-4dce-aeb7-520c7ef76171" because filename "5620e0c7-8062-4dce-aeb7-520c7ef76171" did not match expected pattern of [0-9a-f]+:[0-9a-f]+:[0-9a-f]+[.][0-9a-f]+ -[INFO] 2026-11-09 04:20:02,908 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:20:02,910 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-11-09 04:20:03,002 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:20:03,002 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx -[INFO] 2026-11-09 04:20:03,058 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-11-09 04:20:03,058 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx - Loading weights: 0%| | 0/770 [00:00