feat: Enhance document processing and analysis features
- Added support for processing DOCX files and extracting content. - Updated database schema to include a combined 'issues_and_recommendations' field. - Improved error handling during document uploads and analysis. - Modified the analysis display to show issues and recommendations in a structured format. - Adjusted API call parameters for better performance and error management.
This commit is contained in:
boladeE
@@ -693,3 +693,172 @@ jinja2.exceptions.UndefinedError: list object has no element 1
|
|||||||
2025-04-21 22:33:04,556 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
2025-04-21 22:33:04,556 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
2025-04-21 22:34:43,603 - root - INFO - Document e79aeb90-799a-4d06-9efd-1d19315eebcc processed successfully
|
2025-04-21 22:34:43,603 - root - INFO - Document e79aeb90-799a-4d06-9efd-1d19315eebcc processed successfully
|
||||||
2025-04-21 22:34:43,611 - root - INFO - Document e79aeb90-799a-4d06-9efd-1d19315eebcc processed successfully
|
2025-04-21 22:34:43,611 - root - INFO - Document e79aeb90-799a-4d06-9efd-1d19315eebcc processed successfully
|
||||||
|
2025-04-22 09:39:48,962 - root - INFO - Processing upload for document ID: e838ee14-75a7-483a-9a6e-46b218127dc5
|
||||||
|
2025-04-22 09:39:48,968 - root - INFO - File saved to data/uploads/e838ee14-75a7-483a-9a6e-46b218127dc5_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 09:39:49,014 - root - INFO - Processing document e838ee14-75a7-483a-9a6e-46b218127dc5 with content length: 15335
|
||||||
|
2025-04-22 09:39:50,452 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 09:39:51,219 - root - INFO - Stored embedding for document e838ee14-75a7-483a-9a6e-46b218127dc5
|
||||||
|
2025-04-22 09:41:03,267 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 09:41:56,158 - root - INFO - Document e838ee14-75a7-483a-9a6e-46b218127dc5 processed successfully
|
||||||
|
2025-04-22 09:41:56,169 - root - INFO - Document e838ee14-75a7-483a-9a6e-46b218127dc5 processed successfully
|
||||||
|
2025-04-22 09:50:01,851 - root - INFO - Processing upload for document ID: eaed1290-2993-4133-9a04-6a4e5cb8b431
|
||||||
|
2025-04-22 09:50:01,854 - root - INFO - File saved to data/uploads/eaed1290-2993-4133-9a04-6a4e5cb8b431_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 09:50:02,083 - root - ERROR - Error reading Word document: No module named 'exceptions'
|
||||||
|
2025-04-22 09:50:02,083 - root - INFO - Processing document eaed1290-2993-4133-9a04-6a4e5cb8b431 with content length: 0
|
||||||
|
2025-04-22 09:50:02,520 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 09:50:03,207 - root - INFO - Stored embedding for document eaed1290-2993-4133-9a04-6a4e5cb8b431
|
||||||
|
2025-04-22 09:50:47,257 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 09:51:36,358 - root - INFO - Document eaed1290-2993-4133-9a04-6a4e5cb8b431 processed successfully
|
||||||
|
2025-04-22 09:51:36,377 - root - INFO - Document eaed1290-2993-4133-9a04-6a4e5cb8b431 processed successfully
|
||||||
|
2025-04-22 09:55:01,750 - root - INFO - Processing upload for document ID: aec927db-9f43-49b9-90af-2af8ad64e793
|
||||||
|
2025-04-22 09:55:01,752 - root - INFO - File saved to data/uploads/aec927db-9f43-49b9-90af-2af8ad64e793_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 09:55:01,791 - root - ERROR - Error reading Word document: No module named 'exceptions'
|
||||||
|
2025-04-22 09:55:01,791 - root - INFO - Processing document aec927db-9f43-49b9-90af-2af8ad64e793 with content length: 0
|
||||||
|
2025-04-22 09:55:02,033 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 09:55:02,565 - root - INFO - Stored embedding for document aec927db-9f43-49b9-90af-2af8ad64e793
|
||||||
|
2025-04-22 09:55:57,175 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 09:56:48,889 - root - INFO - Document aec927db-9f43-49b9-90af-2af8ad64e793 processed successfully
|
||||||
|
2025-04-22 09:56:48,898 - root - INFO - Document aec927db-9f43-49b9-90af-2af8ad64e793 processed successfully
|
||||||
|
2025-04-22 10:00:35,648 - root - INFO - Processing upload for document ID: 48480333-d451-4907-988b-f059166fd1a5
|
||||||
|
2025-04-22 10:00:35,652 - root - INFO - File saved to data/uploads/48480333-d451-4907-988b-f059166fd1a5_9.confidentiality agreement.docx
|
||||||
|
2025-04-22 10:00:36,025 - root - INFO - Processing document 48480333-d451-4907-988b-f059166fd1a5 with content length: 161
|
||||||
|
2025-04-22 10:00:36,689 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:00:37,466 - root - INFO - Stored embedding for document 48480333-d451-4907-988b-f059166fd1a5
|
||||||
|
2025-04-22 10:01:31,476 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:02:20,575 - root - INFO - Document 48480333-d451-4907-988b-f059166fd1a5 processed successfully
|
||||||
|
2025-04-22 10:02:20,592 - root - INFO - Document 48480333-d451-4907-988b-f059166fd1a5 processed successfully
|
||||||
|
2025-04-22 10:06:04,139 - root - INFO - Deleted document f1d07dde-5de4-4bf6-a14d-b69a433aa855 from index
|
||||||
|
2025-04-22 10:06:04,142 - root - INFO - Removed document f1d07dde-5de4-4bf6-a14d-b69a433aa855 from vector store
|
||||||
|
2025-04-22 10:06:04,289 - root - ERROR - Error retrieving metadata for document f1d07dde-5de4-4bf6-a14d-b69a433aa855: Metadata not found for document f1d07dde-5de4-4bf6-a14d-b69a433aa855
|
||||||
|
2025-04-22 10:06:04,289 - root - ERROR - Error deleting document: Metadata not found for document f1d07dde-5de4-4bf6-a14d-b69a433aa855
|
||||||
|
2025-04-22 10:06:04,289 - root - ERROR - Traceback (most recent call last):
|
||||||
|
File "C:\Users\babaw\Documents\Work\Mana Knight Digital\ds_task_scp\src\main.py", line 213, in delete_document
|
||||||
|
metadata = database.get_metadata(doc_id)
|
||||||
|
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
||||||
|
File "C:\Users\babaw\Documents\Work\Mana Knight Digital\ds_task_scp\src\services\database.py", line 114, in get_metadata
|
||||||
|
raise FileNotFoundError(f"Metadata not found for document {document_id}")
|
||||||
|
FileNotFoundError: Metadata not found for document f1d07dde-5de4-4bf6-a14d-b69a433aa855
|
||||||
|
|
||||||
|
2025-04-22 10:06:08,722 - root - INFO - Deleted document 82d9da57-6291-4ddb-b2e3-d43f467f4dd0 from index
|
||||||
|
2025-04-22 10:06:08,722 - root - INFO - Removed document 82d9da57-6291-4ddb-b2e3-d43f467f4dd0 from vector store
|
||||||
|
2025-04-22 10:06:13,324 - root - INFO - Deleted uploaded file: data/uploads/78afc395-9b7c-4388-8d8b-aa1d02fbf75f_2.Tender Specifications.docx
|
||||||
|
2025-04-22 10:06:13,533 - root - INFO - Deleted document 78afc395-9b7c-4388-8d8b-aa1d02fbf75f from index
|
||||||
|
2025-04-22 10:06:13,533 - root - INFO - Removed document 78afc395-9b7c-4388-8d8b-aa1d02fbf75f from vector store
|
||||||
|
2025-04-22 10:06:17,591 - root - INFO - Deleted uploaded file: data/uploads/aecbb62c-b7ed-4c2e-beff-fe5e292de9f1_4.Scope of Work.docx
|
||||||
|
2025-04-22 10:06:17,860 - root - INFO - Deleted document aecbb62c-b7ed-4c2e-beff-fe5e292de9f1 from index
|
||||||
|
2025-04-22 10:06:17,860 - root - INFO - Removed document aecbb62c-b7ed-4c2e-beff-fe5e292de9f1 from vector store
|
||||||
|
2025-04-22 10:06:22,432 - root - INFO - Deleted uploaded file: data/uploads/77063b1d-633c-421e-9591-cde2eb90a979_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 10:06:22,572 - root - INFO - Deleted document 77063b1d-633c-421e-9591-cde2eb90a979 from index
|
||||||
|
2025-04-22 10:06:22,572 - root - INFO - Removed document 77063b1d-633c-421e-9591-cde2eb90a979 from vector store
|
||||||
|
2025-04-22 10:06:26,959 - root - INFO - Deleted uploaded file: data/uploads/e79aeb90-799a-4d06-9efd-1d19315eebcc_2.Tender Specifications.docx
|
||||||
|
2025-04-22 10:06:27,114 - root - INFO - Deleted document e79aeb90-799a-4d06-9efd-1d19315eebcc from index
|
||||||
|
2025-04-22 10:06:27,119 - root - INFO - Removed document e79aeb90-799a-4d06-9efd-1d19315eebcc from vector store
|
||||||
|
2025-04-22 10:06:31,340 - root - INFO - Deleted uploaded file: data/uploads/e838ee14-75a7-483a-9a6e-46b218127dc5_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 10:06:31,518 - root - INFO - Deleted document e838ee14-75a7-483a-9a6e-46b218127dc5 from index
|
||||||
|
2025-04-22 10:06:31,520 - root - INFO - Removed document e838ee14-75a7-483a-9a6e-46b218127dc5 from vector store
|
||||||
|
2025-04-22 10:06:50,772 - root - INFO - Processing upload for document ID: 788f85e4-a873-407b-bfbc-0b7d6a676b9a
|
||||||
|
2025-04-22 10:06:50,779 - root - INFO - File saved to data/uploads/788f85e4-a873-407b-bfbc-0b7d6a676b9a_2.Tender Specifications.docx
|
||||||
|
2025-04-22 10:06:51,181 - root - INFO - Processing document 788f85e4-a873-407b-bfbc-0b7d6a676b9a with content length: 2363
|
||||||
|
2025-04-22 10:06:51,477 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:06:52,399 - root - INFO - Stored embedding for document 788f85e4-a873-407b-bfbc-0b7d6a676b9a
|
||||||
|
2025-04-22 10:08:26,609 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:09:18,265 - root - INFO - Document 788f85e4-a873-407b-bfbc-0b7d6a676b9a processed successfully
|
||||||
|
2025-04-22 10:09:18,287 - root - INFO - Document 788f85e4-a873-407b-bfbc-0b7d6a676b9a processed successfully
|
||||||
|
2025-04-22 10:31:42,225 - root - INFO - Processing upload for document ID: 804d09d1-22b8-4e49-9bab-6fd7d34181b7
|
||||||
|
2025-04-22 10:31:42,227 - root - INFO - File saved to data/uploads/804d09d1-22b8-4e49-9bab-6fd7d34181b7_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 10:31:42,381 - root - INFO - Processing document 804d09d1-22b8-4e49-9bab-6fd7d34181b7 with content length: 229
|
||||||
|
2025-04-22 10:31:42,613 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:31:44,246 - root - INFO - Stored embedding for document 804d09d1-22b8-4e49-9bab-6fd7d34181b7
|
||||||
|
2025-04-22 10:32:27,429 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:33:19,434 - root - INFO - Document 804d09d1-22b8-4e49-9bab-6fd7d34181b7 processed successfully
|
||||||
|
2025-04-22 10:33:19,446 - root - INFO - Document 804d09d1-22b8-4e49-9bab-6fd7d34181b7 processed successfully
|
||||||
|
2025-04-22 10:51:21,371 - root - INFO - Processing upload for document ID: 8d580b49-94bb-473e-90dd-66ee00f77048
|
||||||
|
2025-04-22 10:51:21,372 - root - INFO - File saved to data/uploads/8d580b49-94bb-473e-90dd-66ee00f77048_8.form of tender.docx
|
||||||
|
2025-04-22 10:51:21,496 - root - INFO - Processing document 8d580b49-94bb-473e-90dd-66ee00f77048 with content length: 523
|
||||||
|
2025-04-22 10:51:21,994 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:51:22,895 - root - INFO - Stored embedding for document 8d580b49-94bb-473e-90dd-66ee00f77048
|
||||||
|
2025-04-22 10:52:05,978 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 400 Bad Request"
|
||||||
|
2025-04-22 10:52:05,978 - root - ERROR - Error using Cohere reranker: status_code: 400, body: {'message': 'invalid request: number of total max chunks (number of documents * max chunks per doc) must be less than 10000'}
|
||||||
|
2025-04-22 10:56:57,188 - root - INFO - Processing upload for document ID: 5ab90386-7d4e-45b2-a1a6-40ad23f59428
|
||||||
|
2025-04-22 10:56:57,189 - root - INFO - File saved to data/uploads/5ab90386-7d4e-45b2-a1a6-40ad23f59428_8.form of tender.docx
|
||||||
|
2025-04-22 10:56:57,312 - root - INFO - Processing document 5ab90386-7d4e-45b2-a1a6-40ad23f59428 with content length: 523
|
||||||
|
2025-04-22 10:56:57,661 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 10:56:58,794 - root - INFO - Stored embedding for document 5ab90386-7d4e-45b2-a1a6-40ad23f59428
|
||||||
|
2025-04-22 10:57:57,544 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 400 Bad Request"
|
||||||
|
2025-04-22 10:57:57,544 - root - ERROR - Error using Cohere reranker: status_code: 400, body: {'message': 'invalid request: list of documents must not be empty'}
|
||||||
|
2025-04-22 10:57:57,563 - root - INFO - Document 5ab90386-7d4e-45b2-a1a6-40ad23f59428 processed successfully
|
||||||
|
2025-04-22 10:57:57,563 - root - INFO - Document 5ab90386-7d4e-45b2-a1a6-40ad23f59428 processed successfully
|
||||||
|
2025-04-22 11:04:23,803 - root - INFO - Processing upload for document ID: 3065e0dd-0b2e-454c-8f7e-dd0e464dbf7a
|
||||||
|
2025-04-22 11:04:23,806 - root - INFO - File saved to data/uploads/3065e0dd-0b2e-454c-8f7e-dd0e464dbf7a_3.Bill of Quantities.docx
|
||||||
|
2025-04-22 11:04:23,950 - root - INFO - Processing document 3065e0dd-0b2e-454c-8f7e-dd0e464dbf7a with content length: 2057
|
||||||
|
2025-04-22 11:04:24,294 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:04:24,927 - root - INFO - Stored embedding for document 3065e0dd-0b2e-454c-8f7e-dd0e464dbf7a
|
||||||
|
2025-04-22 11:05:28,953 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 400 Bad Request"
|
||||||
|
2025-04-22 11:05:28,953 - root - ERROR - Error using Cohere reranker: status_code: 400, body: {'message': 'invalid request: list of documents must not be empty'}
|
||||||
|
2025-04-22 11:05:28,969 - root - INFO - Document 3065e0dd-0b2e-454c-8f7e-dd0e464dbf7a processed successfully
|
||||||
|
2025-04-22 11:05:28,980 - root - INFO - Document 3065e0dd-0b2e-454c-8f7e-dd0e464dbf7a processed successfully
|
||||||
|
2025-04-22 11:13:54,204 - root - INFO - Processing upload for document ID: 201e4896-3d89-466b-852d-783ef3e30f83
|
||||||
|
2025-04-22 11:13:54,206 - root - INFO - File saved to data/uploads/201e4896-3d89-466b-852d-783ef3e30f83_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 11:13:54,311 - root - INFO - Processing document 201e4896-3d89-466b-852d-783ef3e30f83 with content length: 229
|
||||||
|
2025-04-22 11:13:54,726 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:13:55,243 - root - INFO - Stored embedding for document 201e4896-3d89-466b-852d-783ef3e30f83
|
||||||
|
2025-04-22 11:14:42,644 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 400 Bad Request"
|
||||||
|
2025-04-22 11:14:42,644 - root - ERROR - Error using Cohere reranker: status_code: 400, body: {'message': 'invalid request: list of documents must not be empty'}
|
||||||
|
2025-04-22 11:14:42,644 - root - INFO - Document 201e4896-3d89-466b-852d-783ef3e30f83 processed successfully
|
||||||
|
2025-04-22 11:14:42,659 - root - INFO - Document 201e4896-3d89-466b-852d-783ef3e30f83 processed successfully
|
||||||
|
2025-04-22 11:18:42,103 - root - INFO - Processing upload for document ID: bc1e71ac-6b65-4b2c-b1e8-81844b49ba5d
|
||||||
|
2025-04-22 11:18:42,104 - root - INFO - File saved to data/uploads/bc1e71ac-6b65-4b2c-b1e8-81844b49ba5d_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 11:18:42,225 - root - INFO - Processing document bc1e71ac-6b65-4b2c-b1e8-81844b49ba5d with content length: 229
|
||||||
|
2025-04-22 11:18:42,443 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:18:45,759 - root - INFO - Stored embedding for document bc1e71ac-6b65-4b2c-b1e8-81844b49ba5d
|
||||||
|
2025-04-22 11:19:35,113 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:19:35,138 - root - INFO - Document bc1e71ac-6b65-4b2c-b1e8-81844b49ba5d processed successfully
|
||||||
|
2025-04-22 11:19:35,145 - root - INFO - Document bc1e71ac-6b65-4b2c-b1e8-81844b49ba5d processed successfully
|
||||||
|
2025-04-22 11:27:23,936 - root - INFO - Processing upload for document ID: a76f7f9c-59ec-4f7b-8b4e-168f2db5f92e
|
||||||
|
2025-04-22 11:27:23,938 - root - INFO - File saved to data/uploads/a76f7f9c-59ec-4f7b-8b4e-168f2db5f92e_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 11:27:24,051 - root - INFO - Processing document a76f7f9c-59ec-4f7b-8b4e-168f2db5f92e with content length: 229
|
||||||
|
2025-04-22 11:27:24,259 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:27:24,775 - root - INFO - Stored embedding for document a76f7f9c-59ec-4f7b-8b4e-168f2db5f92e
|
||||||
|
2025-04-22 11:28:04,075 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:28:04,108 - root - INFO - Document a76f7f9c-59ec-4f7b-8b4e-168f2db5f92e processed successfully
|
||||||
|
2025-04-22 11:28:04,108 - root - INFO - Document a76f7f9c-59ec-4f7b-8b4e-168f2db5f92e processed successfully
|
||||||
|
2025-04-22 11:33:42,952 - root - INFO - Processing upload for document ID: 6fd270a4-e76a-4234-a4c4-a40d2ac64d56
|
||||||
|
2025-04-22 11:33:42,954 - root - INFO - File saved to data/uploads/6fd270a4-e76a-4234-a4c4-a40d2ac64d56_4.Scope of Work.docx
|
||||||
|
2025-04-22 11:33:43,183 - root - INFO - Processing document 6fd270a4-e76a-4234-a4c4-a40d2ac64d56 with content length: 282
|
||||||
|
2025-04-22 11:33:43,425 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:33:43,875 - root - INFO - Stored embedding for document 6fd270a4-e76a-4234-a4c4-a40d2ac64d56
|
||||||
|
2025-04-22 11:34:30,942 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:34:30,960 - root - INFO - Document 6fd270a4-e76a-4234-a4c4-a40d2ac64d56 processed successfully
|
||||||
|
2025-04-22 11:34:30,960 - root - INFO - Document 6fd270a4-e76a-4234-a4c4-a40d2ac64d56 processed successfully
|
||||||
|
2025-04-22 11:43:04,651 - root - INFO - Processing upload for document ID: e92e078c-6d36-46b1-89ba-03f7387947e9
|
||||||
|
2025-04-22 11:43:04,652 - root - INFO - File saved to data/uploads/e92e078c-6d36-46b1-89ba-03f7387947e9_9.confidentiality agreement.docx
|
||||||
|
2025-04-22 11:43:04,758 - root - INFO - Processing document e92e078c-6d36-46b1-89ba-03f7387947e9 with content length: 161
|
||||||
|
2025-04-22 11:43:05,057 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:43:05,924 - root - INFO - Stored embedding for document e92e078c-6d36-46b1-89ba-03f7387947e9
|
||||||
|
2025-04-22 11:43:46,791 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/rerank "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:43:46,807 - root - INFO - Document e92e078c-6d36-46b1-89ba-03f7387947e9 processed successfully
|
||||||
|
2025-04-22 11:43:46,807 - root - INFO - Document e92e078c-6d36-46b1-89ba-03f7387947e9 processed successfully
|
||||||
|
2025-04-22 11:52:38,067 - root - INFO - Processing upload for document ID: 2813c3dc-8496-4aff-b945-0b04e5c439c0
|
||||||
|
2025-04-22 11:52:38,069 - root - INFO - File saved to data/uploads/2813c3dc-8496-4aff-b945-0b04e5c439c0_7.Supplier SQualification requirements.docx
|
||||||
|
2025-04-22 11:52:38,184 - root - INFO - Processing document 2813c3dc-8496-4aff-b945-0b04e5c439c0 with content length: 229
|
||||||
|
2025-04-22 11:52:38,574 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:52:39,190 - root - INFO - Stored embedding for document 2813c3dc-8496-4aff-b945-0b04e5c439c0
|
||||||
|
2025-04-22 11:53:23,757 - root - ERROR - Error saving analysis for document 2813c3dc-8496-4aff-b945-0b04e5c439c0: table analysis has no column named issues_and_recommendations
|
||||||
|
2025-04-22 11:53:23,757 - root - ERROR - Error processing document 2813c3dc-8496-4aff-b945-0b04e5c439c0: table analysis has no column named issues_and_recommendations
|
||||||
|
2025-04-22 11:53:23,757 - root - ERROR - Error processing document: table analysis has no column named issues_and_recommendations
|
||||||
|
2025-04-22 11:53:23,783 - root - ERROR - Traceback (most recent call last):
|
||||||
|
File "C:\Users\babaw\Documents\Work\Mana Knight Digital\ds_task_scp\src\main.py", line 112, in upload_document
|
||||||
|
await document_processor.process_document(doc_id, file_path, document_type)
|
||||||
|
File "C:\Users\babaw\Documents\Work\Mana Knight Digital\ds_task_scp\src\services\document_processor.py", line 141, in process_document
|
||||||
|
self.database.save_analysis(doc_id, analysis)
|
||||||
|
File "C:\Users\babaw\Documents\Work\Mana Knight Digital\ds_task_scp\src\services\database.py", line 50, in save_analysis
|
||||||
|
cursor.execute('''
|
||||||
|
sqlite3.OperationalError: table analysis has no column named issues_and_recommendations
|
||||||
|
|
||||||
|
2025-04-22 11:55:32,835 - root - INFO - Processing upload for document ID: 9dc21524-8c93-427b-a6cc-04b7585a9545
|
||||||
|
2025-04-22 11:55:32,836 - root - INFO - File saved to data/uploads/9dc21524-8c93-427b-a6cc-04b7585a9545_8.form of tender.docx
|
||||||
|
2025-04-22 11:55:32,958 - root - INFO - Processing document 9dc21524-8c93-427b-a6cc-04b7585a9545 with content length: 523
|
||||||
|
2025-04-22 11:55:33,174 - httpx - INFO - HTTP Request: POST https://api.cohere.com/v1/embed "HTTP/1.1 200 OK"
|
||||||
|
2025-04-22 11:55:33,740 - root - INFO - Stored embedding for document 9dc21524-8c93-427b-a6cc-04b7585a9545
|
||||||
|
2025-04-22 11:56:27,580 - root - INFO - Document 9dc21524-8c93-427b-a6cc-04b7585a9545 processed successfully
|
||||||
|
2025-04-22 11:56:27,588 - root - INFO - Document 9dc21524-8c93-427b-a6cc-04b7585a9545 processed successfully
|
||||||
|
|||||||
@@ -135,6 +135,7 @@ async def get_analysis(request: Request, doc_id: str):
|
|||||||
analysis = await document_processor.get_analysis(doc_id)
|
analysis = await document_processor.get_analysis(doc_id)
|
||||||
metadata = database.get_metadata(doc_id)
|
metadata = database.get_metadata(doc_id)
|
||||||
|
|
||||||
|
print(f"analysis: {analysis}")
|
||||||
return templates.TemplateResponse(
|
return templates.TemplateResponse(
|
||||||
"analysis.html",
|
"analysis.html",
|
||||||
{
|
{
|
||||||
|
|||||||
+62
-10
@@ -16,13 +16,67 @@ class Database:
|
|||||||
with sqlite3.connect(self.db_path) as conn:
|
with sqlite3.connect(self.db_path) as conn:
|
||||||
cursor = conn.cursor()
|
cursor = conn.cursor()
|
||||||
|
|
||||||
# Create analysis table
|
# Check if we need to migrate the old schema
|
||||||
|
cursor.execute("SELECT name FROM sqlite_master WHERE type='table' AND name='analysis'")
|
||||||
|
table_exists = cursor.fetchone() is not None
|
||||||
|
|
||||||
|
if table_exists:
|
||||||
|
# Check if we need to migrate
|
||||||
|
cursor.execute("PRAGMA table_info(analysis)")
|
||||||
|
columns = [column[1] for column in cursor.fetchall()]
|
||||||
|
|
||||||
|
if 'issues_and_recommendations' not in columns:
|
||||||
|
# Backup old data
|
||||||
|
cursor.execute("SELECT document_id, summary, issues, recommendations FROM analysis")
|
||||||
|
old_data = cursor.fetchall()
|
||||||
|
|
||||||
|
# Drop the old table
|
||||||
|
cursor.execute("DROP TABLE analysis")
|
||||||
|
|
||||||
|
# Create the new table
|
||||||
|
cursor.execute('''
|
||||||
|
CREATE TABLE analysis (
|
||||||
|
document_id TEXT PRIMARY KEY,
|
||||||
|
summary TEXT,
|
||||||
|
issues_and_recommendations TEXT,
|
||||||
|
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||||
|
)
|
||||||
|
''')
|
||||||
|
|
||||||
|
# Migrate old data to new format
|
||||||
|
for row in old_data:
|
||||||
|
doc_id, summary, issues, recommendations = row
|
||||||
|
try:
|
||||||
|
old_issues = json.loads(issues) if issues else []
|
||||||
|
old_recommendations = json.loads(recommendations) if recommendations else []
|
||||||
|
|
||||||
|
# Combine issues and recommendations
|
||||||
|
issues_and_recommendations = []
|
||||||
|
for i in range(max(len(old_issues), len(old_recommendations))):
|
||||||
|
issue = old_issues[i]['issue'] if i < len(old_issues) else "Unknown Issue"
|
||||||
|
recommendation = old_recommendations[i] if i < len(old_recommendations) else "No recommendation provided"
|
||||||
|
issues_and_recommendations.append({
|
||||||
|
"issue": issue,
|
||||||
|
"recommendation": recommendation
|
||||||
|
})
|
||||||
|
|
||||||
|
cursor.execute('''
|
||||||
|
INSERT INTO analysis (document_id, summary, issues_and_recommendations)
|
||||||
|
VALUES (?, ?, ?)
|
||||||
|
''', (
|
||||||
|
doc_id,
|
||||||
|
summary,
|
||||||
|
json.dumps(issues_and_recommendations)
|
||||||
|
))
|
||||||
|
except Exception as e:
|
||||||
|
logging.error(f"Error migrating data for document {doc_id}: {str(e)}")
|
||||||
|
else:
|
||||||
|
# Create the new table if it doesn't exist
|
||||||
cursor.execute('''
|
cursor.execute('''
|
||||||
CREATE TABLE IF NOT EXISTS analysis (
|
CREATE TABLE IF NOT EXISTS analysis (
|
||||||
document_id TEXT PRIMARY KEY,
|
document_id TEXT PRIMARY KEY,
|
||||||
summary TEXT,
|
summary TEXT,
|
||||||
issues TEXT,
|
issues_and_recommendations TEXT,
|
||||||
recommendations TEXT,
|
|
||||||
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
||||||
)
|
)
|
||||||
''')
|
''')
|
||||||
@@ -49,13 +103,12 @@ class Database:
|
|||||||
with sqlite3.connect(self.db_path) as conn:
|
with sqlite3.connect(self.db_path) as conn:
|
||||||
cursor = conn.cursor()
|
cursor = conn.cursor()
|
||||||
cursor.execute('''
|
cursor.execute('''
|
||||||
INSERT OR REPLACE INTO analysis (document_id, summary, issues, recommendations)
|
INSERT OR REPLACE INTO analysis (document_id, summary, issues_and_recommendations)
|
||||||
VALUES (?, ?, ?, ?)
|
VALUES (?, ?, ?)
|
||||||
''', (
|
''', (
|
||||||
document_id,
|
document_id,
|
||||||
analysis['summary'],
|
analysis['summary'],
|
||||||
json.dumps(analysis['issues']),
|
json.dumps(analysis['issues_and_recommendations'])
|
||||||
json.dumps(analysis['recommendations'])
|
|
||||||
))
|
))
|
||||||
conn.commit()
|
conn.commit()
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
@@ -67,7 +120,7 @@ class Database:
|
|||||||
try:
|
try:
|
||||||
with sqlite3.connect(self.db_path) as conn:
|
with sqlite3.connect(self.db_path) as conn:
|
||||||
cursor = conn.cursor()
|
cursor = conn.cursor()
|
||||||
cursor.execute('SELECT summary, issues, recommendations FROM analysis WHERE document_id = ?', (document_id,))
|
cursor.execute('SELECT summary, issues_and_recommendations FROM analysis WHERE document_id = ?', (document_id,))
|
||||||
result = cursor.fetchone()
|
result = cursor.fetchone()
|
||||||
|
|
||||||
if not result:
|
if not result:
|
||||||
@@ -76,8 +129,7 @@ class Database:
|
|||||||
return {
|
return {
|
||||||
'document_id': document_id,
|
'document_id': document_id,
|
||||||
'summary': result[0],
|
'summary': result[0],
|
||||||
'issues': json.loads(result[1]),
|
'issues_and_recommendations': json.loads(result[1])
|
||||||
'recommendations': json.loads(result[2])
|
|
||||||
}
|
}
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logging.error(f"Error retrieving analysis for document {document_id}: {str(e)}")
|
logging.error(f"Error retrieving analysis for document {document_id}: {str(e)}")
|
||||||
|
|||||||
@@ -19,15 +19,16 @@ class DocumentProcessor:
|
|||||||
self.database = Database()
|
self.database = Database()
|
||||||
|
|
||||||
async def process_document(self, doc_id: str, file_path: str, document_type: str, is_resubmission: bool = False):
|
async def process_document(self, doc_id: str, file_path: str, document_type: str, is_resubmission: bool = False):
|
||||||
|
|
||||||
try:
|
try:
|
||||||
# Read document content with error handling for encoding
|
# Read document content with error handling for encoding
|
||||||
try:
|
try:
|
||||||
with open(file_path, 'r', encoding='utf-8') as f:
|
import docx
|
||||||
content = f.read()
|
doc = docx.Document(file_path)
|
||||||
except UnicodeDecodeError:
|
content = "\n".join([para.text for para in doc.paragraphs])
|
||||||
# Try with a different encoding if UTF-8 fails
|
except Exception as e:
|
||||||
with open(file_path, 'r', encoding='latin-1') as f:
|
logging.error(f"Error reading Word document: {str(e)}")
|
||||||
content = f.read()
|
content = ""
|
||||||
|
|
||||||
logging.info(f"Processing document {doc_id} with content length: {len(content)}")
|
logging.info(f"Processing document {doc_id} with content length: {len(content)}")
|
||||||
|
|
||||||
@@ -54,7 +55,7 @@ class DocumentProcessor:
|
|||||||
"content": content
|
"content": content
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"max_tokens": 4000
|
"max_tokens": 1000
|
||||||
}
|
}
|
||||||
|
|
||||||
# Make the API call with error handling
|
# Make the API call with error handling
|
||||||
@@ -84,21 +85,22 @@ class DocumentProcessor:
|
|||||||
logging.error(f"Error calling DeepSeek API: {str(e)}")
|
logging.error(f"Error calling DeepSeek API: {str(e)}")
|
||||||
summary = "Document analysis could not be completed due to API connection issues."
|
summary = "Document analysis could not be completed due to API connection issues."
|
||||||
|
|
||||||
# Process with DeepSeek for deep reasoning using URL
|
# Process with DeepSeek for issues and recommendations
|
||||||
deepseek_payload = {
|
deepseek_payload = {
|
||||||
"model": "deepseek-chat",
|
"model": "deepseek-chat",
|
||||||
"messages": [
|
"messages": [
|
||||||
{
|
{
|
||||||
"role": "system",
|
"role": "system",
|
||||||
"content": "You are an expert in document compliance analysis. Analyze the following document for compliance issues and provide detailed feedback."
|
"content": f"You are an expert in document compliance analysis for this type of document: {document_type}. Analyze the following document for compliance issues and provide detailed feedback."
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"role": "user",
|
"role": "user",
|
||||||
"content": f"""Analyze this type of document {document_type} for compliance issues and provide detailed feedback:\n\n{content}
|
"content": f"""Analyze this type of document {document_type} for compliance issues and provide detailed feedback:\n\n{content}
|
||||||
and these are the main sections of the document:\n\n{summary}"""
|
and these are the main sections of the document:\n\n{summary}..
|
||||||
|
Return the issues and recommendations in a structured format: 'Issue: <issue>. Recommendation: <recommendation>.'"""
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"max_tokens": 4000
|
"max_tokens": 1000
|
||||||
}
|
}
|
||||||
|
|
||||||
# Make the API call with error handling
|
# Make the API call with error handling
|
||||||
@@ -113,39 +115,26 @@ class DocumentProcessor:
|
|||||||
# Check if the response is successful
|
# Check if the response is successful
|
||||||
if deepseek_response.status_code != 200:
|
if deepseek_response.status_code != 200:
|
||||||
logging.error(f"DeepSeek API error: {deepseek_response.status_code} - {deepseek_response.text}")
|
logging.error(f"DeepSeek API error: {deepseek_response.status_code} - {deepseek_response.text}")
|
||||||
# Use a fallback for issues if the API call fails
|
# Use a fallback for issues and recommendations if the API call fails
|
||||||
issues = ["Document analysis could not be completed due to API limitations."]
|
issues_and_recommendations = [{"issue": "Document analysis could not be completed due to API limitations.", "recommendation": "Please try again later."}]
|
||||||
else:
|
else:
|
||||||
# Try to parse the JSON response
|
# Try to parse the JSON response
|
||||||
try:
|
try:
|
||||||
deepseek_result = deepseek_response.json()
|
deepseek_result = deepseek_response.json()
|
||||||
issues = self._extract_issues(deepseek_result['choices'][0]['message']['content'])
|
issues_and_recommendations = self._extract_issues_and_recommendations(deepseek_result['choices'][0]['message']['content'])
|
||||||
except (json.JSONDecodeError, KeyError) as e:
|
except (json.JSONDecodeError, KeyError) as e:
|
||||||
logging.error(f"Error parsing DeepSeek response: {str(e)}")
|
logging.error(f"Error parsing DeepSeek response: {str(e)}")
|
||||||
logging.error(f"Response text: {deepseek_response.text}")
|
logging.error(f"Response text: {deepseek_response.text}")
|
||||||
issues = ["Document analysis could not be completed due to parsing errors."]
|
issues_and_recommendations = [{"issue": "Document analysis could not be completed due to parsing errors.", "recommendation": "Please try again later."}]
|
||||||
except requests.exceptions.RequestException as e:
|
except requests.exceptions.RequestException as e:
|
||||||
logging.error(f"Error calling DeepSeek API: {str(e)}")
|
logging.error(f"Error calling DeepSeek API: {str(e)}")
|
||||||
issues = ["Document analysis could not be completed due to API connection issues."]
|
issues_and_recommendations = [{"issue": "Document analysis could not be completed due to API connection issues.", "recommendation": "Please try again later."}]
|
||||||
|
|
||||||
# Use Cohere reranker to prioritize issues
|
|
||||||
try:
|
|
||||||
reranked_issues = self.cohere_client.rerank(
|
|
||||||
query="Compliance issues in technical document",
|
|
||||||
documents=issues,
|
|
||||||
model=config.COHERE_RERANKER_MODEL
|
|
||||||
)
|
|
||||||
except Exception as e:
|
|
||||||
logging.error(f"Error using Cohere reranker: {str(e)}")
|
|
||||||
# Create a simple reranked issues list if Cohere fails
|
|
||||||
reranked_issues = [type('obj', (object,), {'document': issue, 'index': i}) for i, issue in enumerate(issues)]
|
|
||||||
|
|
||||||
# Store analysis results
|
# Store analysis results
|
||||||
analysis = {
|
analysis = {
|
||||||
"document_id": doc_id,
|
"document_id": doc_id,
|
||||||
"summary": summary,
|
"summary": summary,
|
||||||
"issues": self._format_issues(reranked_issues),
|
"issues_and_recommendations": issues_and_recommendations
|
||||||
"recommendations": self._generate_recommendations(reranked_issues)
|
|
||||||
}
|
}
|
||||||
|
|
||||||
# Save analysis to database
|
# Save analysis to database
|
||||||
@@ -176,72 +165,93 @@ class DocumentProcessor:
|
|||||||
async def get_analysis(self, doc_id: str) -> Dict[str, Any]:
|
async def get_analysis(self, doc_id: str) -> Dict[str, Any]:
|
||||||
return self.database.get_analysis(doc_id)
|
return self.database.get_analysis(doc_id)
|
||||||
|
|
||||||
def _extract_issues(self, deepseek_response: str) -> List[str]:
|
def _extract_issues_and_recommendations(self, deepseek_response: str) -> List[Dict[str, str]]:
|
||||||
# Simple extraction of issues from DeepSeek's response
|
# Extract issues and recommendations from DeepSeek's response
|
||||||
# In a real implementation, this would be more sophisticated
|
|
||||||
print(deepseek_response)
|
|
||||||
return [issue.strip() for issue in re.split(r'\d+\.', deepseek_response) if issue.strip()]
|
|
||||||
|
|
||||||
def _format_issues(self, reranked_issues) -> List[Dict[str, Any]]:
|
issues_and_recommendations = []
|
||||||
return [
|
|
||||||
{
|
|
||||||
"issue": issue[0] if isinstance(issue, tuple) else issue.document,
|
|
||||||
"severity": "high" if i < 3 else "medium" if i < 6 else "low",
|
|
||||||
"rank": i + 1
|
|
||||||
}
|
|
||||||
for i, issue in enumerate(reranked_issues)
|
|
||||||
]
|
|
||||||
|
|
||||||
def _generate_recommendations(self, reranked_issues) -> List[str]:
|
# Split the response into lines
|
||||||
# Generate specific recommendations for each issue
|
lines = deepseek_response.split('\n')
|
||||||
recommendations = []
|
|
||||||
print(f"Generating recommendations for {reranked_issues} issues")
|
|
||||||
# Extract the results from the RerankResponse object
|
|
||||||
results = reranked_issues.results if hasattr(reranked_issues, 'results') else reranked_issues
|
|
||||||
|
|
||||||
for issue in results[:5]: # Focus on top 5 issues
|
current_issue = None
|
||||||
recommendation_payload = {
|
current_recommendation = None
|
||||||
"model": "deepseek-chat",
|
|
||||||
"messages": [
|
|
||||||
{
|
|
||||||
"role": "system",
|
|
||||||
"content": "You are an expert in document compliance. Provide specific, actionable recommendations to fix compliance issues."
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"role": "user",
|
|
||||||
"content": f"Provide a specific, actionable recommendation to fix this compliance issue: {issue}"
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"max_tokens": 1000
|
|
||||||
}
|
|
||||||
|
|
||||||
# Make the API call with error handling
|
for i, line in enumerate(lines):
|
||||||
try:
|
line = line.strip()
|
||||||
recommendation_response = requests.post(
|
|
||||||
self.deepseek_url,
|
|
||||||
json=recommendation_payload,
|
|
||||||
headers=self.deepseek_headers,
|
|
||||||
timeout=60 # Add timeout
|
|
||||||
)
|
|
||||||
|
|
||||||
# Check if the response is successful
|
# Check if this line contains an issue
|
||||||
if recommendation_response.status_code != 200:
|
if '**Issue:**' in line:
|
||||||
logging.error(f"DeepSeek API error: {recommendation_response.status_code} - {recommendation_response.text}")
|
# If we already have an issue and recommendation, add them to the list
|
||||||
recommendations.append("Recommendation could not be generated due to API limitations.")
|
if current_issue and current_recommendation:
|
||||||
else:
|
issues_and_recommendations.append({
|
||||||
# Try to parse the JSON response
|
'issue': current_issue,
|
||||||
try:
|
'recommendation': current_recommendation
|
||||||
recommendation_result = recommendation_response.json()
|
})
|
||||||
recommendations.append(recommendation_result['choices'][0]['message']['content'])
|
|
||||||
except (json.JSONDecodeError, KeyError) as e:
|
|
||||||
logging.error(f"Error parsing DeepSeek response: {str(e)}")
|
|
||||||
logging.error(f"Response text: {recommendation_response.text}")
|
|
||||||
recommendations.append("Recommendation could not be generated due to parsing errors.")
|
|
||||||
except requests.exceptions.RequestException as e:
|
|
||||||
logging.error(f"Error calling DeepSeek API: {str(e)}")
|
|
||||||
recommendations.append("Recommendation could not be generated due to API connection issues.")
|
|
||||||
|
|
||||||
return recommendations
|
# Extract the issue text
|
||||||
|
issue_text = line.split('**Issue:**')[1].strip()
|
||||||
|
current_issue = issue_text
|
||||||
|
current_recommendation = None
|
||||||
|
|
||||||
|
# Check if this line contains a recommendation
|
||||||
|
elif '**Recommendation:**' in line:
|
||||||
|
# Extract the recommendation text
|
||||||
|
recommendation_text = line.split('**Recommendation:**')[1].strip()
|
||||||
|
current_recommendation = recommendation_text
|
||||||
|
|
||||||
|
# If we're at the last line and have both issue and recommendation, add them
|
||||||
|
elif i == len(lines) - 1 and current_issue and current_recommendation:
|
||||||
|
issues_and_recommendations.append({
|
||||||
|
'issue': current_issue,
|
||||||
|
'recommendation': current_recommendation
|
||||||
|
})
|
||||||
|
|
||||||
|
# If we still have an issue and recommendation at the end, add them
|
||||||
|
if current_issue and current_recommendation:
|
||||||
|
issues_and_recommendations.append({
|
||||||
|
'issue': current_issue,
|
||||||
|
'recommendation': current_recommendation
|
||||||
|
})
|
||||||
|
|
||||||
|
# If no issues were found, try an alternative approach
|
||||||
|
if not issues_and_recommendations:
|
||||||
|
# Look for numbered issues in the format "1. **Issue:** ... **Recommendation:** ..."
|
||||||
|
for line in lines:
|
||||||
|
if line.strip().startswith(('1.', '2.', '3.', '4.', '5.', '6.', '7.', '8.', '9.')):
|
||||||
|
if '**Issue:**' in line and '**Recommendation:**' in line:
|
||||||
|
parts = line.split('**Recommendation:**')
|
||||||
|
if len(parts) == 2:
|
||||||
|
issue_part = parts[0]
|
||||||
|
recommendation_part = parts[1]
|
||||||
|
|
||||||
|
# Clean up the issue text
|
||||||
|
issue = issue_part.split('**Issue:**')[1].strip()
|
||||||
|
|
||||||
|
# Clean up the recommendation text
|
||||||
|
recommendation = recommendation_part.strip()
|
||||||
|
|
||||||
|
issues_and_recommendations.append({'issue': issue, 'recommendation': recommendation})
|
||||||
|
|
||||||
|
# If still no issues found, try one more approach
|
||||||
|
if not issues_and_recommendations:
|
||||||
|
# Look for any line containing both Issue and Recommendation
|
||||||
|
for line in lines:
|
||||||
|
if 'Issue:' in line and 'Recommendation:' in line:
|
||||||
|
parts = line.split('Recommendation:')
|
||||||
|
if len(parts) == 2:
|
||||||
|
issue_part = parts[0]
|
||||||
|
recommendation_part = parts[1]
|
||||||
|
|
||||||
|
# Clean up the issue text
|
||||||
|
issue = issue_part.replace('Issue:', '').strip()
|
||||||
|
|
||||||
|
# Clean up the recommendation text
|
||||||
|
recommendation = recommendation_part.strip()
|
||||||
|
|
||||||
|
issues_and_recommendations.append({'issue': issue, 'recommendation': recommendation})
|
||||||
|
|
||||||
|
print(f"issues_and_recommendations: {issues_and_recommendations}")
|
||||||
|
return issues_and_recommendations
|
||||||
|
|
||||||
def _store_document(self, doc_id: str, file_path: str):
|
def _store_document(self, doc_id: str, file_path: str):
|
||||||
# save document to vector store
|
# save document to vector store
|
||||||
|
|||||||
+10
-19
@@ -30,25 +30,16 @@
|
|||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<h5 class="card-title">Compliance Issues</h5>
|
<h5 class="card-title">Issues and Recommendations</h5>
|
||||||
<div class="accordion" id="issuesAccordion">
|
<div class="list-group mb-3">
|
||||||
{% for issue in analysis.issues %}
|
{% for item in analysis.issues_and_recommendations %}
|
||||||
<div class="accordion-item">
|
<div class="list-group-item">
|
||||||
<h2 class="accordion-header" id="heading{{ loop.index }}">
|
<div class="mb-2">
|
||||||
<button class="accordion-button {% if not loop.first %}collapsed{% endif %}" type="button" data-bs-toggle="collapse" data-bs-target="#collapse{{ loop.index }}">
|
<strong>Issue:</strong>
|
||||||
<span class="badge bg-{{ 'danger' if issue.severity == 'high' else 'warning' if issue.severity == 'medium' else 'info' }} me-2">
|
<p class="mb-3">{{ item.issue }}</p>
|
||||||
{{ issue.severity|title }}
|
<strong>Recommendation:</strong>
|
||||||
</span>
|
<div class="alert alert-info markdown-body mt-2">
|
||||||
{{ issue.issue }}
|
{{ item.recommendation|markdown|safe }}
|
||||||
</button>
|
|
||||||
</h2>
|
|
||||||
<div id="collapse{{ loop.index }}" class="accordion-collapse collapse {% if loop.first %}show{% endif %}" data-bs-parent="#issuesAccordion">
|
|
||||||
<div class="accordion-body">
|
|
||||||
<p><strong>Rank:</strong> {{ issue.rank }}</p>
|
|
||||||
<p><strong>Recommendation:</strong></p>
|
|
||||||
<div class="alert alert-info markdown-body">
|
|
||||||
{{ analysis.recommendations[loop.index0]|markdown|safe }}
|
|
||||||
</div>
|
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
|
|||||||
@@ -27,7 +27,7 @@
|
|||||||
<div class="mb-3">
|
<div class="mb-3">
|
||||||
<label for="documentFile" class="form-label">Document File</label>
|
<label for="documentFile" class="form-label">Document File</label>
|
||||||
<input class="form-control" type="file" id="documentFile" name="file" required>
|
<input class="form-control" type="file" id="documentFile" name="file" required>
|
||||||
<div class="form-text">Supported formats: PDF, DOCX, TXT, MD</div>
|
<div class="form-text">Supported formats: DOCX</div>
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
<div class="d-grid">
|
<div class="d-grid">
|
||||||
|
|||||||
Reference in New Issue
Block a user