opendataloarder gets stuck

Author: abhaysapCreated Aug 17, 2026Updated Aug 17, 2026
Labelsbug

Bug

opendataloarder gets stuck when we try to convert pdf to md in hybrid mode

Steps to reproduce

on server

bash: /home/sunny/perl5/perlbrew/etc/bashrc: No such file or directory sunny@sunny-XPS-15-9510:~$ source /venvs/opendataloader/bin/activate (opendataloader) sunny@sunny-XPS-15-9510:$ opendataloader-pdf-hybrid --port 5002 --ocr-engine auto --enrich-formula --enrich-picture-description 2026-08-17 17:06:13,749 - INFO - Loading plugin 'docling_defaults' 2026-08-17 17:06:13,758 - INFO - Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] 2026-08-17 17:06:14,317 - INFO - Accelerator: CPU (no GPU detected) 2026-08-17 17:06:14,317 - INFO - Starting Docling Fast Server on http://0.0.0.0:5002 2026-08-17 17:06:14,317 - INFO - OCR settings: do_ocr=True, ocr_engine=auto, force_ocr=False, lang=default 2026-08-17 17:06:14,317 - INFO - Max file size: unlimited 2026-08-17 17:06:14,317 - INFO - Enrichments enabled: formula, picture-description INFO: Started server process [452660] INFO: Waiting for application startup. 2026-08-17 17:06:14,348 - INFO - Initializing DocumentConverter (do_ocr=True, ocr_engine=auto, force_ocr=False, lang=default, enrichments=formula,picture-description, device=auto)... 2026-08-17 17:06:16,227 - INFO - DocumentConverter initialized in 1.88s INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:5002 (Press CTRL+C to quit) INFO: 127.0.0.1:50250 - "GET /health HTTP/1.1" 200 OK 2026-08-17 17:11:32,914 - INFO - detected formats: [<InputFormat.PDF: 'pdf'>] 2026-08-17 17:11:32,992 - INFO - Going to convert document batch... 2026-08-17 17:11:32,993 - INFO - Initializing pipeline for StandardPdfPipeline with options hash 7060884fc20f485e6edab632a836312e 2026-08-17 17:11:32,995 - INFO - Loading plugin 'docling_defaults' 2026-08-17 17:11:32,997 - INFO - Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] 2026-08-17 17:11:33,331 - INFO - HTTP Request: GET https://huggingface.co/api/agent-harnesses "HTTP/1.1 200 OK" 2026-08-17 17:11:33,589 - INFO - HTTP Request: GET https://huggingface.co/api/models/HuggingFaceTB/SmolVLM-256M-Instruct/revision/main "HTTP/1.1 200 OK" 2026-08-17 17:11:33,655 - INFO - Accelerator device: 'cpu' [transformers] Model config: pad_token_id must be None or an integer within the vocabulary (between 0 and 31999), got 128002. This may result in unexpected behavior. Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 471/471 [00:00<00:00, 5774.81it/s] 2026-08-17 17:11:34,198 - INFO - Nemotron cannot be used because it is not installed. 2026-08-17 17:11:34,198 - INFO - rapidocr cannot be used because onnxruntime is not installed. 2026-08-17 17:11:34,232 - INFO - Accelerator device: 'cpu' /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/ao/nn/quantized/dynamic/modules/rnn.py:162: UserWarning: torch.quantize_per_tensor, torch.quantize_per_channel and other quantized tensor creation functions that produce tensors with dtype torch.quint8, torch.qint8, and torch.qint32 are deprecated and will be removed in a future PyTorch release. Please see https://github.com/pytorch/pytorch/issues/184982 for more information. (Triggered internally at /__w/pytorch/pytorch/aten/src/ATen/quantized/Quantizer.cpp:111.) w_ih = torch.quantize_per_tensor( 2026-08-17 17:11:35,731 - INFO - Auto OCR model selected easyocr. 2026-08-17 17:11:35,736 - INFO - Loading plugin 'docling_defaults' 2026-08-17 17:11:35,738 - INFO - Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] 2026-08-17 17:11:35,746 - INFO - Accelerator device: 'cpu' 2026-08-17 17:11:35,991 - INFO - HTTP Request: GET https://huggingface.co/api/models/docling-project/docling-layout-heron/revision/main "HTTP/1.1 200 OK" Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 770/770 [00:00<00:00, 8790.46it/s] 2026-08-17 17:11:36,256 - INFO - Loading plugin 'docling_defaults' 2026-08-17 17:11:36,258 - INFO - Registered table structure engines: ['docling_tableformer', 'docling_tableformer_v2', 'granite_vision_table'] 2026-08-17 17:11:36,506 - INFO - HTTP Request: GET https://huggingface.co/api/models/docling-project/docling-models/revision/v2.3.0 "HTTP/1.1 200 OK" 2026-08-17 17:11:36,538 - INFO - Accelerator device: 'cpu' 2026-08-17 17:11:36,981 - INFO - Initializing CodeFormulaVlmModel with runtime system: model=docling-project/CodeFormulaV2, engine=auto_inline 2026-08-17 17:11:36,982 - INFO - Initializing auto-inline VLM inference engine... 2026-08-17 17:11:36,982 - INFO - Accelerator device: 'cpu' 2026-08-17 17:11:36,982 - INFO - Auto-selecting engine for system=Linux, device=cpu 2026-08-17 17:11:36,982 - INFO - Selected Transformers engine (default) 2026-08-17 17:11:36,982 - INFO - Generated config for transformers: repo_id=docling-project/CodeFormulaV2, extra_config={'transformers_model_type': <TransformersModelType.AUTOMODEL_IMAGETEXTTOTEXT: 'automodel-imagetexttotext'>, 'extra_generation_config': {'skip_special_tokens': False}, 'torch_dtype': 'bfloat16'} 2026-08-17 17:11:36,983 - INFO - Initializing Transformers VLM inference engine... 2026-08-17 17:11:36,983 - INFO - Accelerator device: 'cpu' 2026-08-17 17:11:36,983 - INFO - Using device: cpu 2026-08-17 17:11:36,983 - INFO - Loading model docling-project/CodeFormulaV2 (revision: main, model_type: automodel-imagetexttotext) 2026-08-17 17:11:37,234 - INFO - HTTP Request: GET https://huggingface.co/api/models/docling-project/CodeFormulaV2/revision/main "HTTP/1.1 200 OK" Loading weights: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 471/471 [00:00<00:00, 4342.06it/s] [transformers] The tied weights mapping and config for this model specifies to tie model.text_model.embed_tokens.weight to lm_head.weight, but both are present in the checkpoints with different values, so we will NOT tie them. You should update the config with tie_word_embeddings=False to silence this warning. 2026-08-17 17:11:38,366 - INFO - Loaded model docling-project/CodeFormulaV2 (revision: main) 2026-08-17 17:11:38,366 - INFO - Auto-inline engine initialized with transformers 2026-08-17 17:11:38,366 - INFO - CodeFormulaVlmModel initialized successfully 2026-08-17 17:11:38,366 - INFO - Processing document tmp_lpzdi27.pdf /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/python3.14/site-packages/torch/utils/data/dataloader.py:759: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used. super().init(loader) /home/sunny/venvs/opendataloader/lib/

Source: opendataloader-project/opendataloader-pdf