| (venv) PS D:\AI\chatbot> $env:HF_HUB_DISABLE_XET = "1" |
| (venv) PS D:\AI\chatbot> python extractor.py |
| Initialising Docling models.... |
| Docling ready, starting extraction now..... |
| Found 1 PDFs |
| 0%| | 0/1 [00:00<?, ?it/s] |
| Processing 4b14d418_Advisor_2022-06-22T14_02_00.454Z.pdf |
|
|
| Starting conversion for 4b14d418_Advisor_2022-06-22T14_02_00.454Z.pdf... |
| INFO:docling.datamodel.document:detected formats: [<InputFormat.PDF: 'pdf'>] |
| INFO:docling.document_converter:Going to convert document batch... |
| INFO:docling.document_converter:Initializing pipeline for StandardPdfPipeline with options hash 051c1e157cd81d4fe9f97027ec51ea64 |
| INFO:docling.models.factories.base_factory:Loading plugin 'docling_defaults' |
| INFO:docling.models.factories:Registered picture descriptions: ['picture_description_vlm_engine', 'vlm', 'api'] |
| INFO:docling.models.factories.base_factory:Loading plugin 'docling_defaults' |
| INFO:docling.models.factories:Registered ocr engines: ['auto', 'easyocr', 'kserve_v2_ocr', 'nemotron-ocr', 'ocrmac', 'rapidocr', 'tesserocr', 'tesseract'] |
| INFO:docling.models.factories.base_factory:Loading plugin 'docling_defaults' |
| INFO:docling.models.factories:Registered layout engines: ['layout_object_detection', 'docling_layout_default', 'docling_experimental_table_crops_layout'] |
| INFO:docling.utils.accelerator_utils:Accelerator device: 'cpu' |
| DEBUG:httpcore.connection:connect_tcp.started host='huggingface.co' port=443 local_address=None timeout=None socket_options=None |
| DEBUG:httpcore.connection:connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x000001E3F1550790> |
| DEBUG:httpcore.connection:start_tls.started ssl_context=<ssl.SSLContext object at 0x000001E3F1CF7020> server_hostname='huggingface.co' timeout=None |
| DEBUG:httpcore.connection:start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x000001E3F1549450> |
| DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:send_request_headers.complete |
| DEBUG:httpcore.http11:send_request_body.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:send_request_body.complete |
| DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Content-Type', b'application/json; charset=utf-8'), (b'Content-Length', b'983'), (b'Connection', b'keep-alive'), (b'Date', b'Tue, 21 Jul 2026 08:21:42 GMT'), (b'ETag', b'W/"3d7-got+AUXlxl8GPv1wjmsyKP26mNw"'), (b'X-Powered-By', b'huggingface-moon'), (b'X-Request-Id', b'Root=1-6a5f2c16-2cc2a50e065ada863ebf1211;6fb4c7ca-cfd0-4d53-9492-c330035cc6d5'), (b'RateLimit', b'"api";r=499;t=206'), (b'RateLimit-Policy', b'"fixed window";"api";q=500;w=300'), (b'cross-origin-opener-policy', b'same-origin'), (b'Referrer-Policy', b'strict-origin-when-cross-origin'), (b'Access-Control-Max-Age', b'86400'), (b'Access-Control-Allow-Origin', b'https://huggingface.co'), (b'Vary', b'Origin'), (b'Access-Control-Expose-Headers', b'X-Repo-Commit,X-Request-Id,X-Error-Code,X-Error-Message,X-Total-Count,ETag,Link,Accept-Ranges,Content-Range,X-Linked-Size,X-Linked-ETag,X-Xet-Hash'), (b'X-Cache', b'Miss from cloudfront'), (b'Via', b'1.1 d86cc37936c4c581f4f46ca0b7a8effa.cloudfront.net (CloudFront)'), (b'X-Amz-Cf-Pop', b'DXB53-P3'), (b'Alt-Svc', b'h3=":443"; ma=86400'), (b'X-Amz-Cf-Id', b'W5IE7iJhEslxq3N6w31hcrFVY3jbcTrhzlPkquBdogOs8M12o9bhMw==')]) |
| INFO:httpx:HTTP Request: GET https://huggingface.co/api/models/docling-project/docling-layout-heron/revision/main "HTTP/1.1 200 OK" |
| DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:receive_response_body.complete |
| DEBUG:httpcore.http11:response_closed.started |
| DEBUG:httpcore.http11:response_closed.complete |
| DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'HEAD']> |
| DEBUG:httpcore.http11:send_request_headers.complete |
| DEBUG:httpcore.http11:send_request_body.started request=<Request [b'HEAD']> |
| DEBUG:httpcore.http11:send_request_body.complete |
| DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'HEAD']> |
| DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 302, b'Found', [(b'Content-Type', b'text/plain; charset=utf-8'), (b'Content-Length', b'982'), (b'Connection', b'keep-alive'), (b'Date', b'Tue, 21 Jul 2026 08:21:42 GMT'), (b'Location', b'https://us.aws.cdn.hf.co/xet-bridge-us/67fe52e0b3a9473353b72227/14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model.safetensors%3B+filename%3D%22model.safetensors%22%3B&user_id=public&X-Xet-Cas-Uid=public&Expires=1784625702&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly91cy5hd3MuY2RuLmhmLmNvL3hldC1icmlkZ2UtdXMvNjdmZTUyZTBiM2E5NDczMzUzYjcyMjI3LzE0MzU2MDkxZWYxMWRiYjUzODdkZjEzZjYzNjEwZjIyYmFmNzg2OTQ3ZjUxZjAyNTNjODI2OTgwZDE1ZmNiOGJcXD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPWlubGluZSUzQitmaWxlbmFtZSUyQSUzRFVURi04JTI3JTI3bW9kZWwuc2FmZXRlbnNvcnMlM0IrZmlsZW5hbWUlM0QlMjJtb2RlbC5zYWZldGVuc29ycyUyMiUzQiZ1c2VyX2lkPXB1YmxpYyZYLVhldC1DYXMtVWlkPXB1YmxpYyIsIkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiRXBvY2hUaW1lIjoxNzg0NjI1NzAyfX19XX0_&Signature=MEUCIQCPEQ6cxp6bD0InaM-8SOgiiZeNbgtsIPgHyMhS0wqFOgIgA9%7EwxriVaNGlumvQYPJW078oOAFVKNPLqXgi2p2vKks_&Key-Pair-Id=01KXEF4KZ1B6FV465MAWR4M21F'), (b'X-Powered-By', b'huggingface-moon'), (b'X-Request-Id', b'Root=1-6a5f2c16-3d530fa01843a16765c95d7a;5a6cca58-293b-4313-87b3-2fa19bca0e94'), (b'RateLimit', b'"resolvers";r=2999;t=206'), (b'RateLimit-Policy', b'"fixed window";"resolvers";q=3000;w=300'), (b'cross-origin-opener-policy', b'same-origin'), (b'Referrer-Policy', b'strict-origin-when-cross-origin'), (b'Access-Control-Max-Age', b'86400'), (b'Access-Control-Allow-Origin', b'https://huggingface.co'), (b'Vary', b'Origin, Accept'), (b'Access-Control-Expose-Headers', b'X-Repo-Commit,X-Request-Id,X-Error-Code,X-Error-Message,X-Total-Count,ETag,Link,Accept-Ranges,Content-Range,X-Linked-Size,X-Linked-ETag,X-Xet-Hash'), (b'X-Repo-Commit', b'8f39ad3c0b4c58e9c2d2c84a38465abf757272d8'), (b'Accept-Ranges', b'bytes'), (b'X-Hub-Cache', b'HIT'), (b'X-Linked-Size', b'171658996'), (b'X-Linked-ETag', b'"00333a43451945aaf89db8ca9c0a17e75d1537c17db60fdb91aa95f4c7929e0c"'), (b'Cache-Control', b'no-store'), (b'X-Xet-Hash', b'14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b'), (b'Link', b'<https://huggingface.co/api/models/docling-project/docling-layout-heron/xet-read-token/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8>; rel="xet-auth", <https://cas-server.xethub.hf.co/v1/reconstructions/14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b>; rel="xet-reconstruction-info"'), (b'X-Cache', b'Miss from cloudfront'), (b'Via', b'1.1 d86cc37936c4c581f4f46ca0b7a8effa.cloudfront.net (CloudFront)'), (b'X-Amz-Cf-Pop', b'DXB53-P3'), (b'Alt-Svc', b'h3=":443"; ma=86400'), (b'X-Amz-Cf-Id', b'mAdp_-gzwv-IUFCmdt57Ex93Jf8FcC4hDVhwJ_klXHRPwcgpRdbULQ==')]) |
| INFO:httpx:HTTP Request: HEAD https://huggingface.co/docling-project/docling-layout-heron/resolve/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8/model.safetensors "HTTP/1.1 302 Found" |
| DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'HEAD']> |
| DEBUG:httpcore.http11:receive_response_body.complete |
| DEBUG:httpcore.http11:response_closed.started |
| DEBUG:httpcore.http11:response_closed.complete |
| DEBUG:filelock:Attempting to acquire lock 2078528098768 on D:\hf_cache\hub\.locks\models--docling-project--docling-layout-heron\00333a43451945aaf89db8ca9c0a17e75d1537c17db60fdb91aa95f4c7929e0c.lock |
| DEBUG:filelock:Lock 2078528098768 acquired on D:\hf_cache\hub\.locks\models--docling-project--docling-layout-heron\00333a43451945aaf89db8ca9c0a17e75d1537c17db60fdb91aa95f4c7929e0c.lock |
| DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:send_request_headers.complete |
| DEBUG:httpcore.http11:send_request_body.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:send_request_body.complete |
| DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 302, b'Found', [(b'Content-Type', b'text/plain; charset=utf-8'), (b'Content-Length', b'982'), (b'Connection', b'keep-alive'), (b'Date', b'Tue, 21 Jul 2026 08:21:43 GMT'), (b'Location', b'https://us.aws.cdn.hf.co/xet-bridge-us/67fe52e0b3a9473353b72227/14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model.safetensors%3B+filename%3D%22model.safetensors%22%3B&user_id=public&X-Xet-Cas-Uid=public&Expires=1784625703&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly91cy5hd3MuY2RuLmhmLmNvL3hldC1icmlkZ2UtdXMvNjdmZTUyZTBiM2E5NDczMzUzYjcyMjI3LzE0MzU2MDkxZWYxMWRiYjUzODdkZjEzZjYzNjEwZjIyYmFmNzg2OTQ3ZjUxZjAyNTNjODI2OTgwZDE1ZmNiOGJcXD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPWlubGluZSUzQitmaWxlbmFtZSUyQSUzRFVURi04JTI3JTI3bW9kZWwuc2FmZXRlbnNvcnMlM0IrZmlsZW5hbWUlM0QlMjJtb2RlbC5zYWZldGVuc29ycyUyMiUzQiZ1c2VyX2lkPXB1YmxpYyZYLVhldC1DYXMtVWlkPXB1YmxpYyIsIkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiRXBvY2hUaW1lIjoxNzg0NjI1NzAzfX19XX0_&Signature=MEUCIQCOvtpBi2O2Ys8VPjHcCV5uSjut0gMaN%7EyTVO5G7ZIYHAIgOrwRU7bdp21T74Kc14ivA1bkvHqrioOyniWg2JyEOKE_&Key-Pair-Id=01KXEF4KZ1B6FV465MAWR4M21F'), (b'X-Powered-By', b'huggingface-moon'), (b'X-Request-Id', b'Root=1-6a5f2c17-66b5831b5a010b24721a84ef;cad7e3d0-a953-4e7c-b058-833642d806a5'), (b'RateLimit', b'"resolvers";r=2998;t=205'), (b'RateLimit-Policy', b'"fixed window";"resolvers";q=3000;w=300'), (b'cross-origin-opener-policy', b'same-origin'), (b'Referrer-Policy', b'strict-origin-when-cross-origin'), (b'Access-Control-Max-Age', b'86400'), (b'Access-Control-Allow-Origin', b'https://huggingface.co'), (b'Vary', b'Origin, Accept'), (b'Access-Control-Expose-Headers', b'X-Repo-Commit,X-Request-Id,X-Error-Code,X-Error-Message,X-Total-Count,ETag,Link,Accept-Ranges,Content-Range,X-Linked-Size,X-Linked-ETag,X-Xet-Hash'), (b'X-Repo-Commit', b'8f39ad3c0b4c58e9c2d2c84a38465abf757272d8'), (b'Accept-Ranges', b'bytes'), (b'X-HF-Warning', b'unauthenticated; Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.'), (b'X-Linked-Size', b'171658996'), (b'X-Linked-ETag', b'"00333a43451945aaf89db8ca9c0a17e75d1537c17db60fdb91aa95f4c7929e0c"'), (b'Cache-Control', b'no-store'), (b'X-Xet-Hash', b'14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b'), (b'Link', b'<https://huggingface.co/api/models/docling-project/docling-layout-heron/xet-read-token/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8>; rel="xet-auth", <https://cas-server.xethub.hf.co/v1/reconstructions/14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b>; rel="xet-reconstruction-info"'), (b'X-Cache', b'Miss from cloudfront'), (b'Via', b'1.1 d86cc37936c4c581f4f46ca0b7a8effa.cloudfront.net (CloudFront)'), (b'X-Amz-Cf-Pop', b'DXB53-P3'), (b'Alt-Svc', b'h3=":443"; ma=86400'), (b'X-Amz-Cf-Id', b'mQrnF0zFHnhIB3_S5qpT0Oyr4Y8ew6HOS3vUnl-jLvNdnvgK9c_eew==')]) |
| INFO:httpx:HTTP Request: GET https://huggingface.co/docling-project/docling-layout-heron/resolve/8f39ad3c0b4c58e9c2d2c84a38465abf757272d8/model.safetensors "HTTP/1.1 302 Found" |
| DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:receive_response_body.complete |
| DEBUG:httpcore.http11:response_closed.started |
| DEBUG:httpcore.http11:response_closed.complete |
| DEBUG:httpcore.connection:connect_tcp.started host='us.aws.cdn.hf.co' port=443 local_address=None timeout=10 socket_options=None |
| DEBUG:httpcore.connection:connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x000001E3F153B110> |
| DEBUG:httpcore.connection:start_tls.started ssl_context=<ssl.SSLContext object at 0x000001E3F1CF7020> server_hostname='us.aws.cdn.hf.co' timeout=10 |
| DEBUG:httpcore.connection:start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x000001E3F1539910> |
| DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:send_request_headers.complete |
| DEBUG:httpcore.http11:send_request_body.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:send_request_body.complete |
| DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'GET']> |
| DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'content-type', b'application/octet-stream'), (b'accept-ranges', b'bytes'), (b'content-disposition', b'inline; filename*=UTF-8\'\'model.safetensors; filename="model.safetensors";'), (b'etag', b'"14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b"'), (b'access-control-allow-headers', b'Content-Range, Content-Type, Content-Disposition, ETag'), (b'access-control-expose-headers', b'*'), (b'content-length', b'171658996'), (b'vary', b'origin, access-control-request-method, access-control-request-headers'), (b'access-control-allow-origin', b'*'), (b'x-request-id', b'01KY1W8FWN06WTMEH4T46MFXD7'), (b'x-hf-cdn-pop', b'aws-ap-southeast-1'), (b'date', b'Tue, 21 Jul 2026 08:21:44 GMT'), (b'alt-svc', b'h3=":443";ma=60;')]) |
| INFO:httpx:HTTP Request: GET https://us.aws.cdn.hf.co/xet-bridge-us/67fe52e0b3a9473353b72227/14356091ef11dbb5387df13f63610f22baf786947f51f0253c826980d15fcb8b?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27model.safetensors%3B+filename%3D%22model.safetensors%22%3B&user_id=public&X-Xet-Cas-Uid=public&Expires=1784625703&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly91cy5hd3MuY2RuLmhmLmNvL3hldC1icmlkZ2UtdXMvNjdmZTUyZTBiM2E5NDczMzUzYjcyMjI3LzE0MzU2MDkxZWYxMWRiYjUzODdkZjEzZjYzNjEwZjIyYmFmNzg2OTQ3ZjUxZjAyNTNjODI2OTgwZDE1ZmNiOGJcXD9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPWlubGluZSUzQitmaWxlbmFtZSUyQSUzRFVURi04JTI3JTI3bW9kZWwuc2FmZXRlbnNvcnMlM0IrZmlsZW5hbWUlM0QlMjJtb2RlbC5zYWZldGVuc29ycyUyMiUzQiZ1c2VyX2lkPXB1YmxpYyZYLVhldC1DYXMtVWlkPXB1YmxpYyIsIkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiRXBvY2hUaW1lIjoxNzg0NjI1NzAzfX19XX0_&Signature=MEUCIQCOvtpBi2O2Ys8VPjHcCV5uSjut0gMaN%7EyTVO5G7ZIYHAIgOrwRU7bdp21T74Kc14ivA1bkvHqrioOyniWg2JyEOKE_&Key-Pair-Id=01KXEF4KZ1B6FV465MAWR4M21F "HTTP/1.1 200 OK" |
| DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'GET']> |
|
|
