Update app.py

app.py

@@ -486,6 +486,52 @@ import re
 
 #     return final_response
 
+# def clean_response(response_text):
+#     # Remove system and user tags
+#     response_text = re.sub(r'<\|system\|>.*?<\|end\|>', '', response_text, flags=re.DOTALL)
+#     response_text = re.sub(r'<\|user\|>.*?<\|end\|>', '', response_text, flags=re.DOTALL)
+#     response_text = re.sub(r'<\|assistant\|>', '', response_text, flags=re.DOTALL)
+
+#     # Extract the document name and page number
+#     document_match = re.search(r"Document\(metadata=\{'source':'(.+?)','page':(\d+)\}", response_text)
+#     document_match = re.search(r"Document\(metadata=\{'source':'(.+?)','page':(\d+)\}", response_text)
+#     if document_match:
+#         document_name = document_match.group(1).split('/')[-1]  # Get the document name
+#         page_number = document_match.group(2)  # Get the page number
+#     else:
+#         document_name = "Unknown"
+#         page_number = "Unknown"
+
+#     # Remove the entire 'Document(metadata=...' and any mention of it from the response
+#     response_text = re.sub(r'Document\(metadata=\{.*?\},page_content=', '', response_text, flags=re.DOTALL)
+    
+#     # Remove any mention of "Document:" in the response
+#     response_text = re.sub(r'- Document:.*', '', response_text)
+
+#     # Remove any unwanted escape characters like \u and \u00
+#     response_text = re.sub(r'\\u[0-9A-Fa-f]{4}', '', response_text)
+
+#     # Ensure proper spacing between words and dates
+#     response_text = re.sub(r'([a-zA-Z])(\d)', r'\1 \2', response_text)
+#     response_text = re.sub(r'(\d)([a-zA-Z])', r'\1 \2', response_text)
+
+#     # Remove the phrase "Sure! The Responses are as follows:" from the actual content
+#     response_text = re.sub(r'Sure! The Responses are as follows:', '', response_text).strip()
+
+#     # Clean up the text by removing extra whitespace
+#     cleaned_response = re.sub(r'\s+', ' ', response_text).strip()
+
+#     # Format the final response with bullet points
+#     final_response = f"""
+# Sure! Here is the response for your Query:
+# • Document name - {document_name}
+# • Page No - {page_number}
+# • Response - {cleaned_response}
+# """
+
+#     return final_response
+
+
 def clean_response(response_text):
     # Remove system and user tags
     response_text = re.sub(r'<\|system\|>.*?<\|end\|>', '', response_text, flags=re.DOTALL)
@@ -493,10 +539,10 @@ def clean_response(response_text):
     response_text = re.sub(r'<\|assistant\|>', '', response_text, flags=re.DOTALL)
 
     # Extract the document name and page number
-    document_match = re.search(r"Document\(metadata=\{'source':'(.+?)','page':(\d+)\}", response_text)
+    document_match = re.search(r"(\d{6,})_(\d{12,})_V\d+\.pdf,page:(\d+)", response_text)
     if document_match:
-        document_name = document_match.group(1).split('/')[-1]  # Get the document name
-        page_number = document_match.group(2)  # Get the page number
+        document_name = document_match.group(0).split(',')[0]  # Get the document name (before ',page')
+        page_number = document_match.group(3)  # Get the page number
     else:
         document_name = "Unknown"
         page_number = "Unknown"