debug ip

app.py

@@ -246,15 +246,15 @@ async def chat(query, history, sources, reports, subtype, year, client_ip=None,
         "client_location": session_data['location_info'],
         "session_duration_seconds": session_duration,
         # "system_prompt": SYSTEM_PROMPT,
-        "sources": sources,
-        "reports": reports,
-        "subtype": subtype,
+        # "sources": sources,
+        # "reports": reports,
+        # "subtype": subtype,
         "year": year,
         "question": query,
         "retriever": model_config.get('retriever','MODEL'),
         "endpoint_type": model_config.get('reader','TYPE'),
         "reader": model_config.get('reader','NVIDIA_MODEL'),
-        "docs": [doc.page_content for doc in context_retrieved],
+        # "docs": [doc.page_content for doc in context_retrieved],
         "answer": "",
         "time": timestamp,
     }
@@ -539,6 +539,7 @@ with gr.Blocks(title="Audit Q&A", css= "style.css", theme=theme,elem_id = "main-
     
     feedback_thanks = gr.Markdown("Thanks for the feedback!", visible=False)
     feedback_state = gr.State()  # Add state to store logs data
+    debug_ip = gr.Markdown(visible=False)  # Add debug display for IP
 
     def show_feedback(logs):
         """Show feedback buttons and store logs in state"""
@@ -546,22 +547,24 @@ with gr.Blocks(title="Audit Q&A", css= "style.css", theme=theme,elem_id = "main-
 
     def submit_feedback_okay(logs_data):
         """Handle 'okay' feedback submission"""
-        return submit_feedback("okay", logs_data)
+        ip = logs_data.get('client_ip', 'No IP found')
+        return submit_feedback("okay", logs_data) + (gr.update(visible=True, value=f"Debug - Client IP: {ip}"),)
 
     def submit_feedback_not_okay(logs_data):
         """Handle 'not okay' feedback submission"""
-        return submit_feedback("not_okay", logs_data)
+        ip = logs_data.get('client_ip', 'No IP found')
+        return submit_feedback("not_okay", logs_data) + (gr.update(visible=True, value=f"Debug - Client IP: {ip}"),)
     
     okay_btn.click(
         submit_feedback_okay,
         [feedback_state],
-        [feedback_row, feedback_thanks]
+        [feedback_row, feedback_thanks, debug_ip]
     )
     
     not_okay_btn.click(
         submit_feedback_not_okay,
         [feedback_state],
-        [feedback_row, feedback_thanks]
+        [feedback_row, feedback_thanks, debug_ip]
     )
 
     #-------------------- Gradio voodoo continued -------------------------

app_interactions.jsonl

@@ -0,0 +1,4 @@
+{"session_id": "6b4e8dba-4839-4d6b-b1b4-2a45224a5a18", "client_ip": "127.0.0.1", "client_location": {"city": null, "region": null, "country": null, "latitude": null, "longitude": null}, "session_duration_seconds": 3e-06, "year": ["2023"], "question": "What are the key findings of this audit report?", "retriever": "BAAI/bge-large-en-v1.5", "endpoint_type": "DEDICATED", "reader": "meta-llama/Llama-3.1-8B-Instruct", "answer": "The audit reports provided cover the financial statements of Kifamba District Local Government and Buhweju District Local Government for the year ended 30th June 2023. The key findings from these reports are: 1. Management of Government Salary Payroll: * The Minister of Finance, Planning and Economic Development highlighted that expenditure on wage is a substantial percentage of all entity budgets, but significant results have not been achieved despite reforms <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. * A special audit on wage payroll in Local Government entities was carried out to establish the root causes of delays in salary payments and propose remedial measures. The audit covered four FYs from 2019/2020 to 2022/2023, and a separate detailed audit report was issued <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. 2. Implementation of Budget: * The Auditor General's report for Kifamba District Local Government found that the implementation of the approved budget was partially implemented, with some projects still ongoing <a href=\"#doc2\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>2</sup></span></a>. 3 Despite the Codeua ", "time": "1739433242.166489"}
+{"session_id": "6b4e8dba-4839-4d6b-b1b4-2a45224a5a18", "client_ip": "127.0.0.1", "client_location": {"city": null, "region": null, "country": null, "latitude": null, "longitude": null}, "session_duration_seconds": 3e-06, "year": ["2023"], "question": "What are the key findings of this audit report?", "retriever": "BAAI/bge-large-en-v1.5", "endpoint_type": "DEDICATED", "reader": "meta-llama/Llama-3.1-8B-Instruct", "answer": "The audit reports provided cover the financial statements of Kifamba District Local Government and Buhweju District Local Government for the year ended 30th June 2023. The key findings from these reports are: 1. Management of Government Salary Payroll: * The Minister of Finance, Planning and Economic Development highlighted that expenditure on wage is a substantial percentage of all entity budgets, but significant results have not been achieved despite reforms <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. * A special audit on wage payroll in Local Government entities was carried out to establish the root causes of delays in salary payments and propose remedial measures. The audit covered four FYs from 2019/2020 to 2022/2023, and a separate detailed audit report was issued <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. 2. Implementation of Budget: * The Auditor General's report for Kifamba District Local Government found that the implementation of the approved budget was partially implemented, with some projects still ongoing <a href=\"#doc2\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>2</sup></span></a>. 3 Despite the Codeua ", "time": "1739433242.166489", "feedback": "okay"}
+{"session_id": "cf8aac12-a43a-4098-8868-e5f5b113426f", "client_ip": "127.0.0.1", "client_location": {"city": null, "region": null, "country": null, "latitude": null, "longitude": null}, "session_duration_seconds": 3e-06, "year": ["2023"], "question": "What are the key findings of this audit report?", "retriever": "BAAI/bge-large-en-v1.5", "endpoint_type": "DEDICATED", "reader": "meta-llama/Llama-3.1-8B-Instruct", "answer": "The audit reports provided cover the financial statements of Kifamba District Local Government and Buhweju District Local Government for the year ended 30th June 2023. The key findings from these reports are: 1. Management of Government Salary Payroll: * The Minister of Finance, Planning and Economic Development highlighted that expenditure on wage is a substantial percentage of all entity budgets, but significant results have not been achieved despite reforms <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. * A special audit on wage payroll in Local Government entities was carried out to establish the root causes of delays in salary payments and propose remedial measures. The audit covered four FYs from 2019/2020 to 2022/2023, and a separate detailed audit report was issued <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. 2. Implementation of Budget: * The Auditor General's report for Kifamba District Local Government found that the implementation of the approved budget was partially implemented, with some projects still ongoing <a href=\"#doc2\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>2</sup></span></a>. 3 Despite the Codeua ", "time": "1739434342.056213"}
+{"session_id": "cf8aac12-a43a-4098-8868-e5f5b113426f", "client_ip": "127.0.0.1", "client_location": {"city": null, "region": null, "country": null, "latitude": null, "longitude": null}, "session_duration_seconds": 3e-06, "year": ["2023"], "question": "What are the key findings of this audit report?", "retriever": "BAAI/bge-large-en-v1.5", "endpoint_type": "DEDICATED", "reader": "meta-llama/Llama-3.1-8B-Instruct", "answer": "The audit reports provided cover the financial statements of Kifamba District Local Government and Buhweju District Local Government for the year ended 30th June 2023. The key findings from these reports are: 1. Management of Government Salary Payroll: * The Minister of Finance, Planning and Economic Development highlighted that expenditure on wage is a substantial percentage of all entity budgets, but significant results have not been achieved despite reforms <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. * A special audit on wage payroll in Local Government entities was carried out to establish the root causes of delays in salary payments and propose remedial measures. The audit covered four FYs from 2019/2020 to 2022/2023, and a separate detailed audit report was issued <a href=\"#doc1\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>1</sup></span></a>. 2. Implementation of Budget: * The Auditor General's report for Kifamba District Local Government found that the implementation of the approved budget was partially implemented, with some projects still ongoing <a href=\"#doc2\" class=\"a-doc-ref\" target=\"_self\"><span class='doc-ref'><sup>2</sup></span></a>. 3 Despite the Codeua ", "time": "1739434342.056213", "feedback": "okay"}

logs/app.log

@@ -1090,3 +1090,134 @@ Test 0in  ảiul
 2025-02-13 07:17:15,093 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
 2025-02-13 07:17:15,093 - auditqa.reader - INFO - Serverless InferenceClient initialization successful
 2025-02-13 07:19:20,936 - __main__ - INFO - App launched
+2025-02-13 07:43:14,991 - datasets - INFO - PyTorch version 2.4.0 available.
+2025-02-13 07:43:15,120 - sentence_transformers.SentenceTransformer - INFO - Load pretrained SentenceTransformer: BAAI/bge-large-en-v1.5
+2025-02-13 07:43:18,073 - httpx - INFO - HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
+2025-02-13 07:43:18,107 - httpx - INFO - HTTP Request: GET http://127.0.0.1:7860/startup-events "HTTP/1.1 200 OK"
+2025-02-13 07:43:18,121 - httpx - INFO - HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK"
+2025-02-13 07:43:18,664 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-02-13 07:43:22,199 - __main__ - DEBUG - Chat function called with query: What are the key findings of this audit report?
+2025-02-13 07:43:22,200 - __main__ - DEBUG - Client IP: 127.0.0.1
+2025-02-13 07:43:22,200 - __main__ - DEBUG - Session ID: None
+2025-02-13 07:43:22,467 - __main__ - DEBUG - Created new session: 227fc37b-3cf7-4bc3-a630-eb58ef196e3a
+2025-02-13 07:43:22,467 - __main__ - DEBUG - Session duration: 3e-06
+2025-02-13 07:43:22,471 - auditqa.retriever - INFO - Retriever activated
+2025-02-13 07:43:23,482 - sentence_transformers.cross_encoder.CrossEncoder - INFO - Use pytorch device: mps
+2025-02-13 07:43:26,064 - httpx - INFO - HTTP Request: POST https://ff3f0448-0a00-470e-9956-49efa3071db3.europe-west3-0.gcp.cloud.qdrant.io:6333/collections/allreports/points/search "HTTP/1.1 200 OK"
+2025-02-13 07:43:28,226 - auditqa.retriever - INFO - retrieved paragraphs:3
+2025-02-13 07:43:28,422 - auditqa.reader - INFO - Serverless endpoint activated
+2025-02-13 07:43:28,422 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
+2025-02-13 07:43:28,422 - auditqa.reader - INFO - Serverless InferenceClient initialization successful
+2025-02-13 07:44:42,901 - __main__ - INFO - App launched
+2025-02-13 07:44:48,975 - datasets - INFO - PyTorch version 2.4.0 available.
+2025-02-13 07:44:49,076 - sentence_transformers.SentenceTransformer - INFO - Load pretrained SentenceTransformer: BAAI/bge-large-en-v1.5
+2025-02-13 07:44:53,684 - httpx - INFO - HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
+2025-02-13 07:44:53,688 - httpx - INFO - HTTP Request: GET http://127.0.0.1:7860/startup-events "HTTP/1.1 200 OK"
+2025-02-13 07:44:53,700 - httpx - INFO - HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK"
+2025-02-13 07:44:54,257 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-02-13 07:44:58,687 - __main__ - DEBUG - Chat function called with query: What were the most significant areas of non-compliance in this audit?
+2025-02-13 07:44:58,688 - __main__ - DEBUG - Client IP: 127.0.0.1
+2025-02-13 07:44:58,688 - __main__ - DEBUG - Session ID: None
+2025-02-13 07:44:58,936 - __main__ - DEBUG - Created new session: d78e2330-7f60-43ef-9ee1-a3c988763d44
+2025-02-13 07:44:58,937 - __main__ - DEBUG - Session duration: 2e-06
+2025-02-13 07:44:58,938 - auditqa.retriever - INFO - Retriever activated
+2025-02-13 07:45:00,018 - sentence_transformers.cross_encoder.CrossEncoder - INFO - Use pytorch device: mps
+2025-02-13 07:45:02,174 - httpx - INFO - HTTP Request: POST https://ff3f0448-0a00-470e-9956-49efa3071db3.europe-west3-0.gcp.cloud.qdrant.io:6333/collections/allreports/points/search "HTTP/1.1 200 OK"
+2025-02-13 07:45:04,162 - auditqa.retriever - INFO - retrieved paragraphs:3
+2025-02-13 07:45:04,348 - auditqa.reader - INFO - Serverless endpoint activated
+2025-02-13 07:45:04,348 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
+2025-02-13 07:45:04,348 - auditqa.reader - INFO - Serverless InferenceClient initialization successful
+2025-02-13 07:47:05,011 - __main__ - ERROR - Error in process_stream: 403 Forbidden: None.
+Cannot access content at: https://router.huggingface.co/hf-inference/models/meta-llama/Meta-Llama-3-8B-Instruct/v1/chat/completions.
+Make sure your token has the correct permissions.
+<?xml version="1.0" encoding="UTF-8"?>
+<Error><Code>AccessDenied</Code><Message>Access Denied</Message></Error>
+2025-02-13 07:47:43,576 - __main__ - DEBUG - Chat function called with query: What are the key findings of this audit report?
+2025-02-13 07:47:43,577 - __main__ - DEBUG - Client IP: 127.0.0.1
+2025-02-13 07:47:43,577 - __main__ - DEBUG - Session ID: None
+2025-02-13 07:47:43,878 - __main__ - DEBUG - Created new session: 7f94ed2a-ba7b-42f2-914b-9d369a4f9225
+2025-02-13 07:47:43,878 - __main__ - DEBUG - Session duration: 3e-06
+2025-02-13 07:47:43,879 - auditqa.retriever - INFO - Retriever activated
+2025-02-13 07:47:44,981 - sentence_transformers.cross_encoder.CrossEncoder - INFO - Use pytorch device: mps
+2025-02-13 07:47:47,568 - httpx - INFO - HTTP Request: POST https://ff3f0448-0a00-470e-9956-49efa3071db3.europe-west3-0.gcp.cloud.qdrant.io:6333/collections/allreports/points/search "HTTP/1.1 200 OK"
+2025-02-13 07:47:50,407 - auditqa.retriever - INFO - retrieved paragraphs:3
+2025-02-13 07:47:50,576 - auditqa.reader - INFO - Serverless endpoint activated
+2025-02-13 07:47:50,576 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
+2025-02-13 07:47:50,576 - auditqa.reader - INFO - Serverless InferenceClient initialization successful
+2025-02-13 07:48:55,021 - __main__ - INFO - App launched
+2025-02-13 07:49:02,652 - datasets - INFO - PyTorch version 2.4.0 available.
+2025-02-13 07:49:02,752 - sentence_transformers.SentenceTransformer - INFO - Load pretrained SentenceTransformer: BAAI/bge-large-en-v1.5
+2025-02-13 07:49:04,483 - httpx - INFO - HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
+2025-02-13 07:49:04,509 - httpx - INFO - HTTP Request: GET http://127.0.0.1:7860/startup-events "HTTP/1.1 200 OK"
+2025-02-13 07:49:04,521 - httpx - INFO - HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK"
+2025-02-13 07:49:05,063 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-02-13 07:49:18,270 - __main__ - DEBUG - Chat function called with query: What are the key findings of this audit report?
+2025-02-13 07:49:18,271 - __main__ - DEBUG - Client IP: 127.0.0.1
+2025-02-13 07:49:18,271 - __main__ - DEBUG - Session ID: None
+2025-02-13 07:49:18,581 - __main__ - DEBUG - Created new session: 272129e5-9807-49a9-b7f2-c1338bfe7489
+2025-02-13 07:49:18,582 - __main__ - DEBUG - Session duration: 3e-06
+2025-02-13 07:49:18,582 - auditqa.retriever - INFO - Retriever activated
+2025-02-13 07:49:20,660 - sentence_transformers.cross_encoder.CrossEncoder - INFO - Use pytorch device: mps
+2025-02-13 07:49:22,626 - httpx - INFO - HTTP Request: POST https://ff3f0448-0a00-470e-9956-49efa3071db3.europe-west3-0.gcp.cloud.qdrant.io:6333/collections/allreports/points/search "HTTP/1.1 200 OK"
+2025-02-13 07:49:24,717 - auditqa.retriever - INFO - retrieved paragraphs:3
+2025-02-13 07:49:24,894 - auditqa.reader - INFO - Serverless endpoint activated
+2025-02-13 07:49:24,894 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
+2025-02-13 07:49:24,894 - auditqa.reader - INFO - Serverless InferenceClient initialization successful
+2025-02-13 07:53:43,358 - __main__ - INFO - App launched
+2025-02-13 07:53:50,002 - datasets - INFO - PyTorch version 2.4.0 available.
+2025-02-13 07:53:50,112 - sentence_transformers.SentenceTransformer - INFO - Load pretrained SentenceTransformer: BAAI/bge-large-en-v1.5
+2025-02-13 07:53:51,855 - httpx - INFO - HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
+2025-02-13 07:53:51,906 - httpx - INFO - HTTP Request: GET http://127.0.0.1:7860/startup-events "HTTP/1.1 200 OK"
+2025-02-13 07:53:51,920 - httpx - INFO - HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK"
+2025-02-13 07:53:52,456 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-02-13 07:53:57,113 - __main__ - DEBUG - Chat function called with query: What are the key findings of this audit report?
+2025-02-13 07:53:57,114 - __main__ - DEBUG - Client IP: 127.0.0.1
+2025-02-13 07:53:57,114 - __main__ - DEBUG - Session ID: None
+2025-02-13 07:53:57,383 - __main__ - DEBUG - Created new session: 6b4e8dba-4839-4d6b-b1b4-2a45224a5a18
+2025-02-13 07:53:57,383 - __main__ - DEBUG - Session duration: 3e-06
+2025-02-13 07:53:57,384 - auditqa.retriever - INFO - Retriever activated
+2025-02-13 07:53:58,338 - sentence_transformers.cross_encoder.CrossEncoder - INFO - Use pytorch device: mps
+2025-02-13 07:54:00,018 - httpx - INFO - HTTP Request: POST https://ff3f0448-0a00-470e-9956-49efa3071db3.europe-west3-0.gcp.cloud.qdrant.io:6333/collections/allreports/points/search "HTTP/1.1 200 OK"
+2025-02-13 07:54:01,995 - auditqa.retriever - INFO - retrieved paragraphs:3
+2025-02-13 07:54:02,166 - auditqa.reader - INFO - Serverless endpoint activated
+2025-02-13 07:54:02,166 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
+2025-02-13 07:54:02,166 - auditqa.reader - INFO - Serverless InferenceClient initialization successful
+2025-02-13 07:54:35,558 - __main__ - INFO - App launched
+2025-02-13 07:54:41,498 - datasets - INFO - PyTorch version 2.4.0 available.
+2025-02-13 07:54:41,583 - sentence_transformers.SentenceTransformer - INFO - Load pretrained SentenceTransformer: BAAI/bge-large-en-v1.5
+2025-02-13 07:54:44,100 - httpx - INFO - HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
+2025-02-13 07:54:44,114 - httpx - INFO - HTTP Request: GET http://127.0.0.1:7860/startup-events "HTTP/1.1 200 OK"
+2025-02-13 07:54:44,125 - httpx - INFO - HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK"
+2025-02-13 07:54:44,692 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-02-13 07:54:47,575 - __main__ - DEBUG - Chat function called with query: What are the key findings of this audit report?
+2025-02-13 07:54:47,575 - __main__ - DEBUG - Client IP: 127.0.0.1
+2025-02-13 07:54:47,575 - __main__ - DEBUG - Session ID: None
+2025-02-13 07:54:47,846 - __main__ - DEBUG - Created new session: ac53461d-5cef-44f2-b0b9-33a03eb24b73
+2025-02-13 07:54:47,846 - __main__ - DEBUG - Session duration: 3e-06
+2025-02-13 07:54:47,848 - auditqa.retriever - INFO - Retriever activated
+2025-02-13 07:54:48,929 - sentence_transformers.cross_encoder.CrossEncoder - INFO - Use pytorch device: mps
+2025-02-13 07:54:49,947 - httpx - INFO - HTTP Request: POST https://ff3f0448-0a00-470e-9956-49efa3071db3.europe-west3-0.gcp.cloud.qdrant.io:6333/collections/allreports/points/search "HTTP/1.1 200 OK"
+2025-02-13 07:54:51,758 - auditqa.retriever - INFO - retrieved paragraphs:3
+2025-02-13 07:54:51,933 - auditqa.reader - INFO - Serverless endpoint activated
+2025-02-13 07:54:51,934 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
+2025-02-13 07:54:51,934 - auditqa.reader - INFO - Serverless InferenceClient initialization successful
+2025-02-13 07:54:51,985 - __main__ - ERROR - Error in process_stream: (ProtocolError('Connection aborted.', ConnectionResetError(54, 'Connection reset by peer')), '(Request ID: 283c6c49-a07c-4194-89ca-d6c4a2ba76b6)')
+2025-02-13 08:12:02,953 - __main__ - INFO - App launched
+2025-02-13 08:12:10,140 - datasets - INFO - PyTorch version 2.4.0 available.
+2025-02-13 08:12:10,244 - sentence_transformers.SentenceTransformer - INFO - Load pretrained SentenceTransformer: BAAI/bge-large-en-v1.5
+2025-02-13 08:12:12,075 - httpx - INFO - HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
+2025-02-13 08:12:12,094 - httpx - INFO - HTTP Request: GET http://127.0.0.1:7860/startup-events "HTTP/1.1 200 OK"
+2025-02-13 08:12:12,106 - httpx - INFO - HTTP Request: HEAD http://127.0.0.1:7860/ "HTTP/1.1 200 OK"
+2025-02-13 08:12:12,643 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-02-13 08:12:15,594 - __main__ - DEBUG - Chat function called with query: What are the key findings of this audit report?
+2025-02-13 08:12:15,595 - __main__ - DEBUG - Client IP: 127.0.0.1
+2025-02-13 08:12:15,595 - __main__ - DEBUG - Session ID: None
+2025-02-13 08:12:15,884 - __main__ - DEBUG - Created new session: cf8aac12-a43a-4098-8868-e5f5b113426f
+2025-02-13 08:12:15,884 - __main__ - DEBUG - Session duration: 3e-06
+2025-02-13 08:12:15,885 - auditqa.retriever - INFO - Retriever activated
+2025-02-13 08:12:16,936 - sentence_transformers.cross_encoder.CrossEncoder - INFO - Use pytorch device: mps
+2025-02-13 08:12:19,550 - httpx - INFO - HTTP Request: POST https://ff3f0448-0a00-470e-9956-49efa3071db3.europe-west3-0.gcp.cloud.qdrant.io:6333/collections/allreports/points/search "HTTP/1.1 200 OK"
+2025-02-13 08:12:21,874 - auditqa.retriever - INFO - retrieved paragraphs:3
+2025-02-13 08:12:22,056 - auditqa.reader - INFO - Serverless endpoint activated
+2025-02-13 08:12:22,056 - auditqa.reader - INFO - Initializing InferenceClient with model: meta-llama/Meta-Llama-3-8B-Instruct
+2025-02-13 08:12:22,056 - auditqa.reader - INFO - Serverless InferenceClient initialization successful