From 7dce9810bdc2effeaca6986627d5a3ec18df68cb Mon Sep 17 00:00:00 2001 From: "docling-java-ops[bot]" <245010719+docling-java-ops[bot]@users.noreply.github.com> Date: Mon, 27 Jul 2026 05:21:20 +0000 Subject: [PATCH] docs: Update docling-serve compatibility table (from Version tests run # 61) Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> --- .../docling-serve/serve-compatibility.md | 2541 +++++++++-------- 1 file changed, 1356 insertions(+), 1185 deletions(-) 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 70f4e22..0a581a8 100644 --- a/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md +++ b/docs/src/doc/docs/includes/docling-serve/serve-compatibility.md @@ -1,9 +1,10 @@ -# Results for ghcr.io/docling-project/docling-serve as of 2026-07-20T05:24:58.250779869Z +# Results for ghcr.io/docling-project/docling-serve as of 2026-07-27T05:21:16.757408873Z Here are the results: | Tag | Result | Details | | --- | ------ | ------- | +| v1.27.0 | ✅ SUCCESS | [Click for run details](#v1.27.0-details) | | v1.26.0 | ✅ SUCCESS | [Click for run details](#v1.26.0-details) | | v1.25.0 | ✅ SUCCESS | [Click for run details](#v1.25.0-details) | | v1.24.0 | ✅ SUCCESS | [Click for run details](#v1.24.0-details) | @@ -47,6 +48,173 @@ Here are the results: ## Details +### ghcr.io/docling-project/docling-serve:v1.27.0 + +
+Click to expand + +#### Message + +
+Click to collapse + +~~~markdown +Tag v1.27.0 is ok +~~~ + +
+ + +#### Docling server logs + +
+click to expand + +``` +Starting production server 🚀 + +Server started at http://0.0.0.0:5001 +Documentation at http://0.0.0.0:5001/docs +Scalar docs at http://0.0.0.0:5001/scalar + +Logs: +INFO: 05:20:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:20:59 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:20:59 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:20:59 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:20:59 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/healthz$,/health$,/livez$,/metrics$,/readyz$) +INFO: 05:21:00 - uvicorn.error - Started server process [1] +INFO: 05:21:00 - uvicorn.error - Waiting for application startup. +INFO: 05:21:03 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:21:03 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:21:03 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:21:03 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:21:03 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:21:03 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 118619a1d3ed3b201b814dac997d6742 +INFO: 05:21:03 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:21:03 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 05:21:03 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-07-27 05:21:03.571250156 [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: 05:21:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:21:03,779 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:03,780 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-07-27 05:21:03,837 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:03,837 [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] 2026-07-27 05:21:03,882 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:03,882 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:21:03 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:21:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:21:07 - docling.document_converter - Going to convert document batch... +INFO: 05:21:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:21:07 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:21:07 - docling.document_converter - Finished converting document file in 0.80 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: 05:21:07 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:21:07 - docling_jobkit.convert.results - Processed 1 docs in 0.83 seconds. +INFO: 05:21:07 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job c021b464-0ec3-4c18-9a3f-0b4f407d9935 in 0.83 seconds +INFO: 05:21:07 - uvicorn.access - 172.17.0.1:39382 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:07 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:21:07 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:21:07 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:21:07 - docling_serve.app - [TENANT_ID] Task ef84dead-7d15-4fb8-b6c3-6d084dbcf9a1 created with tenant_id='default' +INFO: 05:21:07 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task ef84dead-7d15-4fb8-b6c3-6d084dbcf9a1 +INFO: 05:21:07 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:21:07 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 83f6e7119a1499def48d21cd30b03869 +INFO: 05:21:07 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:21:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:21:07,709 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:07,709 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-07-27 05:21:07,759 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:07,760 [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] 2026-07-27 05:21:07,816 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:07,816 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:21:07 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:21:07 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:21:09 - docling.document_converter - Going to convert document batch... +INFO: 05:21:09 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:21:09 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:21:09 - docling.document_converter - Finished converting document file in 0.60 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: 05:21:09 - docling_jobkit.convert.results - Processed 1 docs in 0.60 seconds. +INFO: 05:21:09 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job ef84dead-7d15-4fb8-b6c3-6d084dbcf9a1 in 0.60 seconds +INFO: 05:21:09 - uvicorn.access - 172.17.0.1:39382 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:09 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:21:09 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:21:09 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:21:09 - docling_serve.app - [TENANT_ID] Task 4aacc374-3dca-41a8-84e9-80632f602f54 created with tenant_id='default' +INFO: 05:21:09 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 4aacc374-3dca-41a8-84e9-80632f602f54 +INFO: 05:21:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:21:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 528ff53b5cc66cd5f7f61ef2cd72a8fc +INFO: 05:21:09 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:21:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:21:09,725 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:09,726 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/det/PP-OCRv6_det_small.onnx +[INFO] 2026-07-27 05:21:09,774 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:09,775 [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] 2026-07-27 05:21:09,821 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:21:09,821 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv6/rec/PP-OCRv6_rec_small.onnx +INFO: 05:21:09 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:21:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:21:11 - docling.document_converter - Going to convert document batch... +INFO: 05:21:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:21:11 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:21:11 - docling.document_converter - Finished converting document file in 0.62 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: 05:21:11 - docling_jobkit.convert.results - Processed 1 docs in 0.64 seconds. +INFO: 05:21:11 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4aacc374-3dca-41a8-84e9-80632f602f54 in 0.64 seconds +INFO: 05:21:11 - uvicorn.access - 172.17.0.1:39382 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:21:11 - uvicorn.access - 172.17.0.1:39382 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:21:11 - uvicorn.access - 172.17.0.1:39382 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 + +``` + +
+ +
+ ### ghcr.io/docling-project/docling-serve:v1.26.0
@@ -77,136 +245,136 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:24:42 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:24:42 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:24:42 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:24:42 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:24:42 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/health$,/healthz$,/ready$,/readyz$) -INFO: 05:24:43 - uvicorn.error - Started server process [1] -INFO: 05:24:43 - uvicorn.error - Waiting for application startup. -INFO: 05:24:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:24:46 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:24:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:24:46 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:24:46 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:24:46 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 -INFO: 05:24:46 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:24:46 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -INFO: 05:24:46 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -2026-07-20 05:24:46.409905893 [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: 05:24:46 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:24:46,876 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:46,878 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:24:46,967 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:46,967 [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] 2026-07-20 05:24:47,014 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:47,014 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:24:47 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:24:47 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:24:49 - docling.document_converter - Going to convert document batch... -INFO: 05:24:49 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:24:49 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:24:49 - docling.document_converter - Finished converting document file in 0.54 sec. +INFO: 05:19:52 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:52 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:19:52 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:19:52 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:19:52 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/readyz$,/healthz$,/livez$,/metrics$,/health$) +INFO: 05:19:52 - uvicorn.error - Started server process [1] +INFO: 05:19:52 - uvicorn.error - Waiting for application startup. +INFO: 05:19:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:56 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:19:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:56 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:19:56 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:19:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c4d6547d10e26a777a530d63ca01a1a1 +INFO: 05:19:56 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:19:56 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +INFO: 05:19:56 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +2026-07-27 05:19:56.439706321 [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: 05:19:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:19:57,062 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:19:57,064 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:19:57,214 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:19:57,215 [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] 2026-07-27 05:19:57,305 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:19:57,305 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:19:57 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:19:57 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:20:01 - docling.document_converter - Going to convert document batch... +INFO: 05:20:01 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:20:01 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:20:01 - docling.document_converter - Finished converting document file in 0.38 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: 05:24:49 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:24:49 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. -INFO: 05:24:49 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2b9b0f19-3cb1-4c8d-9c12-2feafe211db7 in 0.58 seconds -INFO: 05:24:49 - uvicorn.access - 172.17.0.1:34902 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:24:49 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:24:49 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:24:49 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:24:49 - docling_serve.app - [TENANT_ID] Task 5442cbf4-ef6e-46f0-b338-30670d7e03ca created with tenant_id='default' -INFO: 05:24:49 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5442cbf4-ef6e-46f0-b338-30670d7e03ca -INFO: 05:24:49 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:24:49 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac -INFO: 05:24:49 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 05:24:49 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:24:49,999 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:49,999 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:24:50,090 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:50,090 [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] 2026-07-20 05:24:50,136 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:50,136 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:24:50 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:24:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:24:51 - docling.document_converter - Going to convert document batch... -INFO: 05:24:51 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:24:51 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:24:51 - docling.document_converter - Finished converting document file in 0.50 sec. +WARNING: 05:20:01 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:20:01 - docling_jobkit.convert.results - Processed 1 docs in 0.43 seconds. +INFO: 05:20:01 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4931a440-7157-4e8b-9c47-314eef9c0cda in 0.43 seconds +INFO: 05:20:01 - uvicorn.access - 172.17.0.1:49246 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:20:01 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:20:01 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:20:01 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:20:01 - docling_serve.app - [TENANT_ID] Task 5b5f5280-9043-46f4-8d43-33f2051ae8d1 created with tenant_id='default' +INFO: 05:20:01 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5b5f5280-9043-46f4-8d43-33f2051ae8d1 +INFO: 05:20:01 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:20:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 4ef9920c0fc80ed745870d6025fc17ac +INFO: 05:20:01 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:20:01 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:20:01,709 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:20:01,709 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:20:01,884 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:20:01,885 [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] 2026-07-27 05:20:01,953 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:20:01,954 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:20:02 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:20:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:20:03 - docling.document_converter - Going to convert document batch... +INFO: 05:20:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:20:03 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:20:03 - docling.document_converter - Finished converting document file in 0.44 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: 05:24:51 - docling_jobkit.convert.results - Processed 1 docs in 0.50 seconds. -INFO: 05:24:51 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5442cbf4-ef6e-46f0-b338-30670d7e03ca in 0.50 seconds -INFO: 05:24:51 - uvicorn.access - 172.17.0.1:34902 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:24:51 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:24:51 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:24:51 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:24:51 - docling_serve.app - [TENANT_ID] Task 4239baf7-6f77-4410-ab2b-8534e4a8f970 created with tenant_id='default' -INFO: 05:24:51 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 4239baf7-6f77-4410-ab2b-8534e4a8f970 -INFO: 05:24:51 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:24:51 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 -INFO: 05:24:51 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. -INFO: 05:24:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:24:52,011 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:52,011 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:24:52,101 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:52,102 [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] 2026-07-20 05:24:52,149 [RapidOCR] base.py:23: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:52,150 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:24:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:24:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:24:53 - docling.document_converter - Going to convert document batch... -INFO: 05:24:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:24:53 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:24:53 - docling.document_converter - Finished converting document file in 0.47 sec. +INFO: 05:20:03 - docling_jobkit.convert.results - Processed 1 docs in 0.44 seconds. +INFO: 05:20:03 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5b5f5280-9043-46f4-8d43-33f2051ae8d1 in 0.44 seconds +INFO: 05:20:03 - uvicorn.access - 172.17.0.1:49246 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:20:03 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:20:03 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:20:03 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:20:03 - docling_serve.app - [TENANT_ID] Task 09c78499-c469-4373-a3c9-8c414dbe994c created with tenant_id='default' +INFO: 05:20:03 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 09c78499-c469-4373-a3c9-8c414dbe994c +INFO: 05:20:03 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:20:03 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 63e8839d1103b03d45382915dba33c89 +INFO: 05:20:03 - docling.models.stages.ocr.auto_ocr_model - Nemotron cannot be used because it is not installed. +INFO: 05:20:03 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:20:03,725 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:20:03,726 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:20:03,836 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:20:03,836 [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] 2026-07-27 05:20:03,923 [RapidOCR] base.py:23: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:20:03,923 [RapidOCR] main.py:63: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:20:04 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:20:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:20:05 - docling.document_converter - Going to convert document batch... +INFO: 05:20:05 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:20:05 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:20:05 - 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: 05:24:53 - docling_jobkit.convert.results - Processed 1 docs in 0.49 seconds. -INFO: 05:24:53 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 4239baf7-6f77-4410-ab2b-8534e4a8f970 in 0.49 seconds -INFO: 05:24:53 - uvicorn.access - 172.17.0.1:34902 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:24:54 - uvicorn.access - 172.17.0.1:34902 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:24:54 - uvicorn.access - 172.17.0.1:34902 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:20:05 - docling_jobkit.convert.results - Processed 1 docs in 0.58 seconds. +INFO: 05:20:05 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 09c78499-c469-4373-a3c9-8c414dbe994c in 0.58 seconds +INFO: 05:20:07 - uvicorn.access - 172.17.0.1:49246 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:20:08 - uvicorn.access - 172.17.0.1:49246 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:20:08 - uvicorn.access - 172.17.0.1:49246 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -244,120 +412,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:23:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:23:54 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:23:54 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:23:54 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:23:54 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/healthz$,/metrics$,/health$,/ready$,/readyz$) -INFO: 05:23:55 - uvicorn.error - Started server process [1] -INFO: 05:23:55 - uvicorn.error - Waiting for application startup. -INFO: 05:24:01 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:24:01 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:24:01 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:24:01 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:24:01 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:24:01 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e -INFO: 05:24:01 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:24:01 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-20 05:24:01.431791896 [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: 05:24:02 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:24:03,018 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:03,021 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:24:03,573 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:03,573 [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] 2026-07-20 05:24:03,666 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:03,666 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:24:03 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:24:04 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:24:08 - docling.document_converter - Going to convert document batch... -INFO: 05:24:08 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:24:08 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:24:08 - docling.document_converter - Finished converting document file in 0.79 sec. -WARNING: 05:24:08 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:24:08 - docling_jobkit.convert.results - Processed 1 docs in 0.85 seconds. -INFO: 05:24:08 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 486782e6-7095-420c-8e60-2b52c05db547 in 0.85 seconds -INFO: 05:24:09 - uvicorn.access - 172.17.0.1:48224 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:24:09 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:24:09 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:24:09 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:24:09 - docling_serve.app - [TENANT_ID] Task 0d817ef0-b53b-4237-b988-f8effa6f8265 created with tenant_id='default' -INFO: 05:24:09 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 0d817ef0-b53b-4237-b988-f8effa6f8265 -INFO: 05:24:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:24:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a -INFO: 05:24:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:24:10,020 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:10,020 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:24:10,151 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:10,151 [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] 2026-07-20 05:24:10,198 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:10,198 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:24:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:24:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:24:11 - docling.document_converter - Going to convert document batch... -INFO: 05:24:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:24:11 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:24:12 - docling.document_converter - Finished converting document file in 0.43 sec. -INFO: 05:24:12 - docling_jobkit.convert.results - Processed 1 docs in 0.44 seconds. -INFO: 05:24:12 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 0d817ef0-b53b-4237-b988-f8effa6f8265 in 0.44 seconds -INFO: 05:24:13 - uvicorn.access - 172.17.0.1:48224 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:24:13 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:24:13 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:24:13 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:24:13 - docling_serve.app - [TENANT_ID] Task 1b91ebd1-3aa7-493b-95ac-64bc8094e1cf created with tenant_id='default' -INFO: 05:24:13 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 1b91ebd1-3aa7-493b-95ac-64bc8094e1cf -INFO: 05:24:13 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:24:13 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 -INFO: 05:24:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:24:13,993 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:13,993 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:24:14,131 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:14,131 [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] 2026-07-20 05:24:14,204 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:24:14,205 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:24:14 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:24:14 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:24:16 - docling.document_converter - Going to convert document batch... -INFO: 05:24:16 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:24:16 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:24:16 - docling.document_converter - Finished converting document file in 0.50 sec. -INFO: 05:24:16 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. -INFO: 05:24:16 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 1b91ebd1-3aa7-493b-95ac-64bc8094e1cf in 0.52 seconds -INFO: 05:24:17 - uvicorn.access - 172.17.0.1:48224 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:24:18 - uvicorn.access - 172.17.0.1:48224 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:24:18 - uvicorn.access - 172.17.0.1:48224 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:18:43 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:18:43 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:18:43 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:18:43 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:18:43 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/health$,/ready$,/livez$,/metrics$,/readyz$) +INFO: 05:18:44 - uvicorn.error - Started server process [1] +INFO: 05:18:44 - uvicorn.error - Waiting for application startup. +INFO: 05:18:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:18:49 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:18:49 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:18:49 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:18:49 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:18:50 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash f446dcc5a1a7c6aff458e30cab474a9e +INFO: 05:18:50 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:18:50 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-07-27 05:18:50.164893945 [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: 05:18:50 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:18:50,609 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:18:50,611 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:18:50,751 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:18:50,752 [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] 2026-07-27 05:18:50,815 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:18:50,815 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:18:51 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:18:51 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:18:54 - docling.document_converter - Going to convert document batch... +INFO: 05:18:54 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:18:54 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:18:54 - docling.document_converter - Finished converting document file in 1.03 sec. +WARNING: 05:18:54 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:18:54 - docling_jobkit.convert.results - Processed 1 docs in 1.08 seconds. +INFO: 05:18:54 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 70775e7a-0a2b-4117-8207-7c8e16f0ee4f in 1.08 seconds +INFO: 05:18:56 - uvicorn.access - 172.17.0.1:36590 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:18:56 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:18:56 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:18:56 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:18:56 - docling_serve.app - [TENANT_ID] Task b25b520d-be0f-4473-82a5-d021fcc38f6e created with tenant_id='default' +INFO: 05:18:56 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b25b520d-be0f-4473-82a5-d021fcc38f6e +INFO: 05:18:56 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:18:56 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c639c48e78aacd42b6243acf42ab1c3a +INFO: 05:18:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:18:56,533 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:18:56,533 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:18:56,653 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:18:56,654 [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] 2026-07-27 05:18:56,742 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:18:56,742 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:18:56 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:18:56 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:18:58 - docling.document_converter - Going to convert document batch... +INFO: 05:18:58 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:18:58 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:18:58 - docling.document_converter - Finished converting document file in 0.38 sec. +INFO: 05:18:58 - docling_jobkit.convert.results - Processed 1 docs in 0.38 seconds. +INFO: 05:18:58 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b25b520d-be0f-4473-82a5-d021fcc38f6e in 0.38 seconds +INFO: 05:19:00 - uvicorn.access - 172.17.0.1:36590 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:19:00 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:19:00 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:19:00 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:19:00 - docling_serve.app - [TENANT_ID] Task e3ef2c06-3f56-4a10-809b-799151e7be5b created with tenant_id='default' +INFO: 05:19:00 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task e3ef2c06-3f56-4a10-809b-799151e7be5b +INFO: 05:19:00 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:19:00 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash e50b6140ec7ee9be0d0fea6ba20c9795 +INFO: 05:19:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:19:00,555 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:19:00,555 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:19:00,710 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:19:00,711 [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] 2026-07-27 05:19:00,757 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:19:00,758 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:19:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:19:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:19:02 - docling.document_converter - Going to convert document batch... +INFO: 05:19:02 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:19:02 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:19:02 - docling.document_converter - Finished converting document file in 0.69 sec. +INFO: 05:19:02 - docling_jobkit.convert.results - Processed 1 docs in 0.71 seconds. +INFO: 05:19:02 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job e3ef2c06-3f56-4a10-809b-799151e7be5b in 0.71 seconds +INFO: 05:19:04 - uvicorn.access - 172.17.0.1:36590 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:19:04 - uvicorn.access - 172.17.0.1:36590 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:19:04 - uvicorn.access - 172.17.0.1:36590 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -395,120 +563,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:22:01 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:22:01 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:22:01 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:22:01 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:22:01 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/livez$,/readyz$,/health$,/ready$,/metrics$,/healthz$) -INFO: 05:22:02 - uvicorn.error - Started server process [1] -INFO: 05:22:02 - uvicorn.error - Waiting for application startup. -INFO: 05:22:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:22:05 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:22:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:22:05 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:22:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:22:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 05:22:05 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:22:05 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-20 05:22:05.958359085 [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: 05:22:06 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:22:06,284 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:06,285 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:22:06,391 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:06,391 [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] 2026-07-20 05:22:06,438 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:06,438 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:22:06 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:22:06 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:22:09 - docling.document_converter - Going to convert document batch... -INFO: 05:22:09 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:22:09 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:22:09 - docling.document_converter - Finished converting document file in 1.04 sec. -WARNING: 05:22:09 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:22:10 - docling_jobkit.convert.results - Processed 1 docs in 1.08 seconds. -INFO: 05:22:10 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 46956949-824d-4d2f-b7ff-a20a9eaa0a4b in 1.08 seconds -INFO: 05:22:11 - uvicorn.access - 172.17.0.1:55056 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:22:11 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:22:11 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:22:11 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:22:11 - docling_serve.app - [TENANT_ID] Task b5f9061c-4d63-4017-aa46-5b5b792655e5 created with tenant_id='default' -INFO: 05:22:11 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task b5f9061c-4d63-4017-aa46-5b5b792655e5 -INFO: 05:22:11 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:22:11 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 05:22:11 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:22:11,951 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:11,951 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:22:12,065 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:12,065 [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] 2026-07-20 05:22:12,115 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:12,115 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:22:12 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:22:12 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:22:13 - docling.document_converter - Going to convert document batch... -INFO: 05:22:13 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:22:13 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:22:14 - docling.document_converter - Finished converting document file in 0.74 sec. -INFO: 05:22:14 - docling_jobkit.convert.results - Processed 1 docs in 0.74 seconds. -INFO: 05:22:14 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job b5f9061c-4d63-4017-aa46-5b5b792655e5 in 0.74 seconds -INFO: 05:22:15 - uvicorn.access - 172.17.0.1:55056 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:22:15 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:22:15 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:22:15 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:22:15 - docling_serve.app - [TENANT_ID] Task 8247e99b-f8c0-4ea3-8c4e-8349183f0054 created with tenant_id='default' -INFO: 05:22:15 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 8247e99b-f8c0-4ea3-8c4e-8349183f0054 -INFO: 05:22:15 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:22:15 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 05:22:15 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:22:15,968 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:15,969 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:22:16,063 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:16,063 [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] 2026-07-20 05:22:16,118 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:22:16,118 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:22:16 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:22:16 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:22:17 - docling.document_converter - Going to convert document batch... -INFO: 05:22:17 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:22:17 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:22:17 - docling.document_converter - Finished converting document file in 0.39 sec. -INFO: 05:22:17 - docling_jobkit.convert.results - Processed 1 docs in 0.42 seconds. -INFO: 05:22:17 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8247e99b-f8c0-4ea3-8c4e-8349183f0054 in 0.42 seconds -INFO: 05:22:17 - uvicorn.access - 172.17.0.1:55056 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:22:18 - uvicorn.access - 172.17.0.1:55056 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:22:18 - uvicorn.access - 172.17.0.1:55056 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:17:13 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:13 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:17:13 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:17:13 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:17:13 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/ready$,/livez$,/readyz$,/metrics$,/healthz$,/health$) +INFO: 05:17:14 - uvicorn.error - Started server process [1] +INFO: 05:17:14 - uvicorn.error - Waiting for application startup. +INFO: 05:17:18 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:18 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:17:18 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:18 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:17:18 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:17:18 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 05:17:18 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:17:18 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-07-27 05:17:18.400430280 [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: 05:17:18 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:17:18,728 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:18,730 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:17:18,857 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:18,857 [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] 2026-07-27 05:17:18,945 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:18,946 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:17:19 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:17:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:17:22 - docling.document_converter - Going to convert document batch... +INFO: 05:17:22 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:17:22 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:17:22 - docling.document_converter - Finished converting document file in 0.86 sec. +WARNING: 05:17:22 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:17:22 - docling_jobkit.convert.results - Processed 1 docs in 0.90 seconds. +INFO: 05:17:22 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 208998fc-b062-4ab9-9c58-076a87a73c7b in 0.90 seconds +INFO: 05:17:24 - uvicorn.access - 172.17.0.1:45596 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:17:24 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:17:24 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:17:24 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:17:24 - docling_serve.app - [TENANT_ID] Task 97b272d3-3b90-4bf1-af2e-91c2e1fef929 created with tenant_id='default' +INFO: 05:17:24 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 97b272d3-3b90-4bf1-af2e-91c2e1fef929 +INFO: 05:17:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:17:24 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 05:17:24 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:17:24,597 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:24,597 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:17:24,758 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:24,758 [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] 2026-07-27 05:17:24,809 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:24,809 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:17:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:17:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:17:26 - docling.document_converter - Going to convert document batch... +INFO: 05:17:26 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:17:26 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:17:26 - docling.document_converter - Finished converting document file in 0.36 sec. +INFO: 05:17:26 - docling_jobkit.convert.results - Processed 1 docs in 0.36 seconds. +INFO: 05:17:26 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 97b272d3-3b90-4bf1-af2e-91c2e1fef929 in 0.36 seconds +INFO: 05:17:28 - uvicorn.access - 172.17.0.1:45596 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:17:28 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:17:28 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:17:28 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:17:28 - docling_serve.app - [TENANT_ID] Task 14f8bb7b-6ec9-4938-8beb-73346f7982c9 created with tenant_id='default' +INFO: 05:17:28 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 14f8bb7b-6ec9-4938-8beb-73346f7982c9 +INFO: 05:17:28 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:17:28 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 05:17:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:17:28,631 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:28,631 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:17:28,744 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:28,744 [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] 2026-07-27 05:17:28,829 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:17:28,829 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:17:29 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:17:29 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:17:30 - docling.document_converter - Going to convert document batch... +INFO: 05:17:30 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:17:30 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:17:30 - docling.document_converter - Finished converting document file in 0.61 sec. +INFO: 05:17:30 - docling_jobkit.convert.results - Processed 1 docs in 0.64 seconds. +INFO: 05:17:30 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 14f8bb7b-6ec9-4938-8beb-73346f7982c9 in 0.64 seconds +INFO: 05:17:32 - uvicorn.access - 172.17.0.1:45596 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:17:33 - uvicorn.access - 172.17.0.1:45596 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:17:33 - uvicorn.access - 172.17.0.1:45596 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -546,120 +714,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:21:06 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:21:06 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:21:06 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:21:06 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:21:06 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/metrics$,/livez$,/healthz$,/health$,/readyz$,/ready$) -INFO: 05:21:07 - uvicorn.error - Started server process [1] -INFO: 05:21:07 - uvicorn.error - Waiting for application startup. -INFO: 05:21:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:21:12 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:21:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:21:12 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:21:12 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:21:12 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 05:21:12 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:21:12 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-20 05:21:12.404963671 [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: 05:21:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:21:13,124 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:13,126 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:21:13,268 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:13,268 [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] 2026-07-20 05:21:13,316 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:13,316 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:21:13 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:21:13 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:21:16 - docling.document_converter - Going to convert document batch... -INFO: 05:21:16 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:21:16 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:21:16 - docling.document_converter - Finished converting document file in 0.47 sec. -WARNING: 05:21:17 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:21:17 - docling_jobkit.convert.results - Processed 1 docs in 0.53 seconds. -INFO: 05:21:17 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 43fb0f0a-0041-498a-b0a5-dcffdbf1264c in 0.53 seconds -INFO: 05:21:18 - uvicorn.access - 172.17.0.1:50466 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:21:19 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:21:19 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:21:19 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:21:19 - docling_serve.app - [TENANT_ID] Task e3cb83d6-95d0-4710-948a-531741da6e1b created with tenant_id='default' -INFO: 05:21:19 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task e3cb83d6-95d0-4710-948a-531741da6e1b -INFO: 05:21:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:21:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da -INFO: 05:21:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:21:19,091 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:19,091 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:21:19,211 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:19,211 [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] 2026-07-20 05:21:19,261 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:19,262 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:21:19 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:21:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:21:20 - docling.document_converter - Going to convert document batch... -INFO: 05:21:20 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:21:20 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:21:21 - docling.document_converter - Finished converting document file in 0.51 sec. -INFO: 05:21:21 - docling_jobkit.convert.results - Processed 1 docs in 0.52 seconds. -INFO: 05:21:21 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job e3cb83d6-95d0-4710-948a-531741da6e1b in 0.52 seconds -INFO: 05:21:23 - uvicorn.access - 172.17.0.1:50466 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:21:23 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:21:23 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:21:23 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:21:23 - docling_serve.app - [TENANT_ID] Task a28ecf4a-70da-4c4c-8be0-5376a3860aec created with tenant_id='default' -INFO: 05:21:23 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task a28ecf4a-70da-4c4c-8be0-5376a3860aec -INFO: 05:21:23 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:21:23 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f -INFO: 05:21:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:21:23,139 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:23,140 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:21:23,293 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:23,293 [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] 2026-07-20 05:21:23,381 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:21:23,381 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:21:23 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:21:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:21:24 - docling.document_converter - Going to convert document batch... -INFO: 05:21:24 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:21:24 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:21:24 - docling.document_converter - Finished converting document file in 0.32 sec. -INFO: 05:21:24 - docling_jobkit.convert.results - Processed 1 docs in 0.34 seconds. -INFO: 05:21:24 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job a28ecf4a-70da-4c4c-8be0-5376a3860aec in 0.34 seconds -INFO: 05:21:25 - uvicorn.access - 172.17.0.1:50466 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:21:25 - uvicorn.access - 172.17.0.1:50466 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:21:25 - uvicorn.access - 172.17.0.1:50466 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:16:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:19 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:16:19 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:16:19 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:16:19 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/health$,/healthz$,/metrics$,/ready$,/livez$) +INFO: 05:16:19 - uvicorn.error - Started server process [1] +INFO: 05:16:19 - uvicorn.error - Waiting for application startup. +INFO: 05:16:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:24 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:16:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:24 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:16:24 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:16:24 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 05:16:24 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:16:24 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-07-27 05:16:24.867381595 [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: 05:16:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:16:25,207 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:25,209 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:16:25,371 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:25,371 [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] 2026-07-27 05:16:25,462 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:25,462 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:16:25 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:16:25 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:16:29 - docling.document_converter - Going to convert document batch... +INFO: 05:16:29 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:16:29 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:16:29 - docling.document_converter - Finished converting document file in 0.73 sec. +WARNING: 05:16:29 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:16:29 - docling_jobkit.convert.results - Processed 1 docs in 0.78 seconds. +INFO: 05:16:29 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 2ec89373-2896-4972-8166-ae1ca4df8a9c in 0.78 seconds +INFO: 05:16:31 - uvicorn.access - 172.17.0.1:57308 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:16:31 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:16:31 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:16:31 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:16:31 - docling_serve.app - [TENANT_ID] Task 7c190721-d2b3-41e5-932c-4bec850b632b created with tenant_id='default' +INFO: 05:16:31 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 7c190721-d2b3-41e5-932c-4bec850b632b +INFO: 05:16:31 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:16:31 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 447bb8cb2d04f05cb199adb5a03148da +INFO: 05:16:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:16:31,487 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:31,487 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:16:31,650 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:31,650 [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] 2026-07-27 05:16:31,722 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:31,722 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:16:31 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:16:31 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:16:34 - docling.document_converter - Going to convert document batch... +INFO: 05:16:34 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:16:34 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:16:34 - docling.document_converter - Finished converting document file in 1.19 sec. +INFO: 05:16:34 - docling_jobkit.convert.results - Processed 1 docs in 1.19 seconds. +INFO: 05:16:34 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 7c190721-d2b3-41e5-932c-4bec850b632b in 1.19 seconds +INFO: 05:16:35 - uvicorn.access - 172.17.0.1:57308 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:16:35 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:16:35 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:16:35 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:16:35 - docling_serve.app - [TENANT_ID] Task 44fb0d52-ea01-483e-9133-602fd226433c created with tenant_id='default' +INFO: 05:16:35 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 44fb0d52-ea01-483e-9133-602fd226433c +INFO: 05:16:35 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:16:35 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 6102b5a2a09ce02f29b31fc27cc3d04f +INFO: 05:16:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:16:35,506 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:35,507 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:16:35,645 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:35,645 [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] 2026-07-27 05:16:35,727 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:16:35,728 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:16:35 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:16:35 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:16:37 - docling.document_converter - Going to convert document batch... +INFO: 05:16:37 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:16:37 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:16:37 - docling.document_converter - Finished converting document file in 0.84 sec. +INFO: 05:16:37 - docling_jobkit.convert.results - Processed 1 docs in 0.86 seconds. +INFO: 05:16:37 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 44fb0d52-ea01-483e-9133-602fd226433c in 0.86 seconds +INFO: 05:16:39 - uvicorn.access - 172.17.0.1:57308 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:16:39 - uvicorn.access - 172.17.0.1:57308 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:16:39 - uvicorn.access - 172.17.0.1:57308 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -697,120 +865,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:19:15 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:15 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:19:15 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:19:15 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:19:15 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/ready$,/health$,/livez$,/healthz$,/metrics$) -INFO: 05:19:15 - uvicorn.error - Started server process [1] -INFO: 05:19:15 - uvicorn.error - Waiting for application startup. -INFO: 05:19:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:19 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:19:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:19 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:19:19 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:19:19 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 -INFO: 05:19:19 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:19:19 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-20 05:19:19.546529119 [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: 05:19:19 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:19:19,875 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:19,877 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:19:19,975 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:19,975 [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] 2026-07-20 05:19:20,021 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:20,021 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:19:20 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:19:20 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:19:23 - docling.document_converter - Going to convert document batch... -INFO: 05:19:23 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:19:23 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:19:23 - docling.document_converter - Finished converting document file in 0.70 sec. -WARNING: 05:19:23 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:19:23 - docling_jobkit.convert.results - Processed 1 docs in 0.74 seconds. -INFO: 05:19:23 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8caab8f7-be84-4304-afd7-2a9052d06b60 in 0.74 seconds -INFO: 05:19:23 - uvicorn.access - 172.17.0.1:56704 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:19:23 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:19:23 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:19:23 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:19:23 - docling_serve.app - [TENANT_ID] Task df0a4b07-e24b-4532-961d-bc418cef21b0 created with tenant_id='default' -INFO: 05:19:23 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task df0a4b07-e24b-4532-961d-bc418cef21b0 -INFO: 05:19:23 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:19:23 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 -INFO: 05:19:23 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:19:23,733 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:23,734 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:19:23,826 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:23,826 [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] 2026-07-20 05:19:23,874 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:23,875 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:19:24 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:19:24 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:19:25 - docling.document_converter - Going to convert document batch... -INFO: 05:19:25 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:19:25 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:19:25 - docling.document_converter - Finished converting document file in 0.76 sec. -INFO: 05:19:25 - docling_jobkit.convert.results - Processed 1 docs in 0.77 seconds. -INFO: 05:19:25 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job df0a4b07-e24b-4532-961d-bc418cef21b0 in 0.77 seconds -INFO: 05:19:27 - uvicorn.access - 172.17.0.1:56704 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:19:27 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:19:27 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:19:27 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:19:27 - docling_serve.app - [TENANT_ID] Task ff7055cf-6d64-4545-b23d-b4c6b14d8c56 created with tenant_id='default' -INFO: 05:19:27 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ff7055cf-6d64-4545-b23d-b4c6b14d8c56 -INFO: 05:19:27 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:19:27 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 -INFO: 05:19:27 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:19:27,738 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:27,738 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:19:27,844 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:27,844 [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] 2026-07-20 05:19:27,894 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:19:27,894 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:19:28 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:19:28 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:19:28 - docling.document_converter - Going to convert document batch... -INFO: 05:19:28 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:19:28 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:19:29 - docling.document_converter - Finished converting document file in 0.32 sec. -INFO: 05:19:29 - docling_jobkit.convert.results - Processed 1 docs in 0.34 seconds. -INFO: 05:19:29 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ff7055cf-6d64-4545-b23d-b4c6b14d8c56 in 0.34 seconds -INFO: 05:19:29 - uvicorn.access - 172.17.0.1:56704 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:19:29 - uvicorn.access - 172.17.0.1:56704 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:19:29 - uvicorn.access - 172.17.0.1:56704 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:14:40 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:40 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:14:40 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:14:40 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:14:40 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/health$,/metrics$,/livez$,/ready$,/readyz$,/healthz$) +INFO: 05:14:40 - uvicorn.error - Started server process [1] +INFO: 05:14:40 - uvicorn.error - Waiting for application startup. +INFO: 05:14:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:44 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:14:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:44 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:14:44 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:44 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 1743cd6dac10356c82ba7dfffff4ed02 +INFO: 05:14:44 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:14:44 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-07-27 05:14:44.771474330 [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: 05:14:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:14:45,282 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:45,283 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:14:45,390 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:45,390 [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] 2026-07-27 05:14:45,436 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:45,436 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:48 - docling.document_converter - Going to convert document batch... +INFO: 05:14:48 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:48 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:48 - docling.document_converter - Finished converting document file in 0.75 sec. +WARNING: 05:14:48 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:14:48 - docling_jobkit.convert.results - Processed 1 docs in 0.79 seconds. +INFO: 05:14:48 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 8b2bf131-d0ec-4716-a26d-12b6689a9b30 in 0.79 seconds +INFO: 05:14:48 - uvicorn.access - 172.17.0.1:45852 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:48 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:14:48 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:14:48 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:14:48 - docling_serve.app - [TENANT_ID] Task 90b8336b-f42d-46c5-b291-dac3eb6ace44 created with tenant_id='default' +INFO: 05:14:48 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 90b8336b-f42d-46c5-b291-dac3eb6ace44 +INFO: 05:14:48 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:48 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash a1cb01c48360ff351eb870dc682aac59 +INFO: 05:14:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:14:48,490 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:48,490 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:14:48,592 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:48,593 [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] 2026-07-27 05:14:48,639 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:48,639 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:48 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:48 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:50 - docling.document_converter - Going to convert document batch... +INFO: 05:14:50 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:50 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:50 - docling.document_converter - Finished converting document file in 0.69 sec. +INFO: 05:14:50 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. +INFO: 05:14:50 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 90b8336b-f42d-46c5-b291-dac3eb6ace44 in 0.70 seconds +INFO: 05:14:52 - uvicorn.access - 172.17.0.1:45852 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:52 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:14:52 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:14:52 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:14:52 - docling_serve.app - [TENANT_ID] Task ff805c2c-dc60-4036-8baf-0a7051e8eb82 created with tenant_id='default' +INFO: 05:14:52 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task ff805c2c-dc60-4036-8baf-0a7051e8eb82 +INFO: 05:14:52 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:52 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash fb1751b09de6bdbe35ede48676ca8f82 +INFO: 05:14:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:14:52,506 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:52,506 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:14:52,618 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:52,619 [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] 2026-07-27 05:14:52,666 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:52,666 [RapidOCR] main.py:65: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:52 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:52 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:53 - docling.document_converter - Going to convert document batch... +INFO: 05:14:53 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:53 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:53 - docling.document_converter - Finished converting document file in 0.44 sec. +INFO: 05:14:53 - docling_jobkit.convert.results - Processed 1 docs in 0.46 seconds. +INFO: 05:14:53 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job ff805c2c-dc60-4036-8baf-0a7051e8eb82 in 0.46 seconds +INFO: 05:14:54 - uvicorn.access - 172.17.0.1:45852 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:54 - uvicorn.access - 172.17.0.1:45852 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:14:54 - uvicorn.access - 172.17.0.1:45852 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -848,120 +1016,120 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -INFO: 05:18:27 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:27 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] -INFO: 05:18:27 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics -INFO: 05:18:27 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export -INFO: 05:18:27 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/healthz$,/livez$,/health$,/metrics$,/ready$,/readyz$) -INFO: 05:18:27 - uvicorn.error - Started server process [1] -INFO: 05:18:27 - uvicorn.error - Waiting for application startup. -INFO: 05:18:32 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:32 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] -INFO: 05:18:32 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:32 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] -INFO: 05:18:32 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:18:32 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf -INFO: 05:18:32 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' -INFO: 05:18:32 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] -2026-07-20 05:18:33.055870533 [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: 05:18:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:18:33,586 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:33,589 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:18:33,733 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:33,733 [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] 2026-07-20 05:18:33,780 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:33,781 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:18:33 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:18:33 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:18:38 - docling.document_converter - Going to convert document batch... -INFO: 05:18:38 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:18:38 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:18:38 - docling.document_converter - Finished converting document file in 0.77 sec. -WARNING: 05:18:38 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. -INFO: 05:18:38 - docling_jobkit.convert.results - Processed 1 docs in 0.83 seconds. -INFO: 05:18:38 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 38eff3aa-f1b0-4845-8afb-b8ba988301c1 in 0.83 seconds -INFO: 05:18:40 - uvicorn.access - 172.17.0.1:59198 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:18:40 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:18:40 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:18:40 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:18:40 - docling_serve.app - [TENANT_ID] Task 5269e11a-8b1d-49bc-9ffd-c58fc08a92cc created with tenant_id='default' -INFO: 05:18:40 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task 5269e11a-8b1d-49bc-9ffd-c58fc08a92cc -INFO: 05:18:40 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:18:40 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b -INFO: 05:18:40 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:18:40,910 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:40,910 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:18:41,067 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:41,068 [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] 2026-07-20 05:18:41,174 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:41,174 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:18:41 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:18:41 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:18:43 - docling.document_converter - Going to convert document batch... -INFO: 05:18:43 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:18:43 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:18:43 - docling.document_converter - Finished converting document file in 0.69 sec. -INFO: 05:18:43 - docling_jobkit.convert.results - Processed 1 docs in 0.70 seconds. -INFO: 05:18:43 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job 5269e11a-8b1d-49bc-9ffd-c58fc08a92cc in 0.70 seconds -INFO: 05:18:44 - uvicorn.access - 172.17.0.1:59198 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:18:44 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') -INFO: 05:18:44 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' -INFO: 05:18:44 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata -INFO: 05:18:44 - docling_serve.app - [TENANT_ID] Task 0301461a-2d61-4926-915f-0163b7fe800d created with tenant_id='default' -INFO: 05:18:44 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 0301461a-2d61-4926-915f-0163b7fe800d -INFO: 05:18:44 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. -INFO: 05:18:44 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb -INFO: 05:18:44 - docling.utils.accelerator_utils - Accelerator device: 'cpu' -[INFO] 2026-07-20 05:18:44,924 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:44,924 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:18:45,070 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:45,071 [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] 2026-07-20 05:18:45,161 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:18:45,162 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx -INFO: 05:18:45 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. -INFO: 05:18:45 - docling.utils.accelerator_utils - Accelerator device: 'cpu' - Loading weights: 0%| | 0/770 [00:00] -INFO: 05:18:46 - docling.document_converter - Going to convert document batch... -INFO: 05:18:46 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a -INFO: 05:18:46 - docling.pipeline.base_pipeline - Processing document file -INFO: 05:18:46 - docling.document_converter - Finished converting document file in 0.41 sec. -INFO: 05:18:46 - docling_jobkit.convert.results - Processed 1 docs in 0.45 seconds. -INFO: 05:18:46 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 0301461a-2d61-4926-915f-0163b7fe800d in 0.45 seconds -INFO: 05:18:46 - uvicorn.access - 172.17.0.1:59198 - "POST /v1/convert/source HTTP/1.1" 200 -INFO: 05:18:47 - uvicorn.access - 172.17.0.1:59198 - "GET /v1/clear/converters HTTP/1.1" 200 -INFO: 05:18:47 - uvicorn.access - 172.17.0.1:59198 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 +INFO: 05:13:54 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:13:54 - docling.models.factories - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] +INFO: 05:13:54 - docling_serve.otel_instrumentation - Setting up OpenTelemetry metrics +INFO: 05:13:54 - docling_serve.otel_instrumentation - Enabling Prometheus metrics export +INFO: 05:13:54 - docling_serve.otel_instrumentation - Instrumenting FastAPI with OpenTelemetry (excluded_urls=/readyz$,/livez$,/metrics$,/healthz$,/ready$,/health$) +INFO: 05:13:54 - uvicorn.error - Started server process [1] +INFO: 05:13:54 - uvicorn.error - Waiting for application startup. +INFO: 05:13:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:13:59 - docling.models.factories - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] +INFO: 05:13:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:13:59 - docling.models.factories - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] +INFO: 05:13:59 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:13:59 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash bcb2e23b24bd94a42b5c00d662a7c1cf +INFO: 05:13:59 - docling.models.factories.base_factory - Loading plugin 'docling_defaults' +INFO: 05:13:59 - docling.models.factories - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] +2026-07-27 05:13:59.484703381 [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: 05:13:59 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:13:59,860 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:13:59,862 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:14:00,010 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:00,011 [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] 2026-07-27 05:14:00,080 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:00,080 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:00 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:00 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:03 - docling.document_converter - Going to convert document batch... +INFO: 05:14:03 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:03 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:03 - docling.document_converter - Finished converting document file in 0.89 sec. +WARNING: 05:14:03 - docling_core.types.doc.document - Parameter `strict_text` has been deprecated and will be ignored. +INFO: 05:14:03 - docling_jobkit.convert.results - Processed 1 docs in 0.96 seconds. +INFO: 05:14:03 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 7fb50f4b-5965-41da-b3cf-c630f20fbb78 in 0.96 seconds +INFO: 05:14:05 - uvicorn.access - 172.17.0.1:49452 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:05 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:14:05 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:14:05 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:14:05 - docling_serve.app - [TENANT_ID] Task bfbe5087-37c6-4196-bf63-474fe13ff6e9 created with tenant_id='default' +INFO: 05:14:05 - docling_jobkit.orchestrators.local.worker - Worker 1 processing task bfbe5087-37c6-4196-bf63-474fe13ff6e9 +INFO: 05:14:05 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:05 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash c835e945376007df084ecda847e91f5b +INFO: 05:14:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:14:05,601 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:05,601 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:14:05,722 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:05,723 [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] 2026-07-27 05:14:05,769 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:05,769 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:05 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:05 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:07 - docling.document_converter - Going to convert document batch... +INFO: 05:14:07 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:07 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:07 - docling.document_converter - Finished converting document file in 0.72 sec. +INFO: 05:14:07 - docling_jobkit.convert.results - Processed 1 docs in 0.73 seconds. +INFO: 05:14:07 - docling_jobkit.orchestrators.local.worker - Worker 1 completed job bfbe5087-37c6-4196-bf63-474fe13ff6e9 in 0.73 seconds +INFO: 05:14:09 - uvicorn.access - 172.17.0.1:49452 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Extracted tenant_id from header: 'default' (header_value: 'None') +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] process_url endpoint received tenant_id='default' +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Preparing to enqueue with tenant_id='default' in metadata +INFO: 05:14:09 - docling_serve.app - [TENANT_ID] Task 7524822a-e738-4004-bff1-aed3ea04cea6 created with tenant_id='default' +INFO: 05:14:09 - docling_jobkit.orchestrators.local.worker - Worker 0 processing task 7524822a-e738-4004-bff1-aed3ea04cea6 +INFO: 05:14:09 - docling_jobkit.convert.manager - artifacts_path is set to a valid directory. No model weights will be downloaded at runtime. +INFO: 05:14:09 - docling.document_converter - Initializing pipeline for StandardPdfPipeline with options hash 3eabf304acb4a56e9ef52b02ef69bccb +INFO: 05:14:09 - docling.utils.accelerator_utils - Accelerator device: 'cpu' +[INFO] 2026-07-27 05:14:09,620 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:09,621 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx +[INFO] 2026-07-27 05:14:09,759 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:09,759 [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] 2026-07-27 05:14:09,870 [RapidOCR] base.py:22: Using engine_name: onnxruntime +[INFO] 2026-07-27 05:14:09,871 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx +INFO: 05:14:10 - docling.models.stages.ocr.auto_ocr_model - Auto OCR model selected rapidocr with onnxruntime. +INFO: 05:14:10 - docling.utils.accelerator_utils - Accelerator device: 'cpu' + Loading weights: 0%| | 0/770 [00:00] +INFO: 05:14:11 - docling.document_converter - Going to convert document batch... +INFO: 05:14:11 - docling.document_converter - Initializing pipeline for SimplePipeline with options hash 7d306d2d021deac65a97d1a5f925362a +INFO: 05:14:11 - docling.pipeline.base_pipeline - Processing document file +INFO: 05:14:11 - docling.document_converter - Finished converting document file in 0.44 sec. +INFO: 05:14:11 - docling_jobkit.convert.results - Processed 1 docs in 0.47 seconds. +INFO: 05:14:11 - docling_jobkit.orchestrators.local.worker - Worker 0 completed job 7524822a-e738-4004-bff1-aed3ea04cea6 in 0.47 seconds +INFO: 05:14:11 - uvicorn.access - 172.17.0.1:49452 - "POST /v1/convert/source HTTP/1.1" 200 +INFO: 05:14:11 - uvicorn.access - 172.17.0.1:49452 - "GET /v1/clear/converters HTTP/1.1" 200 +INFO: 05:14:11 - uvicorn.access - 172.17.0.1:49452 - "GET /v1/clear/results?older_then=3600 HTTP/1.1" 200 ``` @@ -999,37 +1167,37 @@ Documentation at http://0.0.0.0:5001/docs Scalar docs at http://0.0.0.0:5001/scalar Logs: -2026-07-20 05:16:30.823050927 [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] 2026-07-20 05:16:31,119 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:16:31,121 [RapidOCR] main.py:57: Using /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx -[INFO] 2026-07-20 05:16:31,213 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:16:31,214 [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] 2026-07-20 05:16:31,260 [RapidOCR] base.py:22: Using engine_name: onnxruntime -[INFO] 2026-07-20 05:16:31,260 [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