post changes

backend/Qdrant.py

@@ -77,12 +77,12 @@ class QdrantManager:
             logger.error(error_msg, exc_info=True)
             raise ValueError(error_msg) from e
 
-# Example usage
-if __name__ == "__main__":
-    try:
-        qdrant_manager = QdrantManager()
-        collection_name = "ca-documents"
-        result = qdrant_manager.get_or_create_company_collection(collection_name)
-        print(f"Collection name: {result}")
-    except Exception as e:
-        print(f"Error: {e}")
+# # Example usage
+# if __name__ == "__main__":
+#     try:
+#         qdrant_manager = QdrantManager()
+#         collection_name = "ca-documents"
+#         result = qdrant_manager.get_or_create_company_collection(collection_name)
+#         print(f"Collection name: {result}")
+#     except Exception as e:
+#         print(f"Error: {e}")

backend/rag.py

@@ -189,10 +189,3 @@ if __name__ == "__main__":
         google_api_key="your_google_api_key",
         collection_name="ca-documents"
     )
-    
-    # Upload documents
-    # rag.upload_document("path/to/your/ca_document.pdf")
-    
-    # Ask questions
-    # answer = rag.ask_question("What is depreciation?")
-    # print(answer) 

backend/vector_store.py

@@ -233,70 +233,6 @@ class VectorStore:
             print(f"Error searching: {e}")
             return []
     
-    def search_by_document_id(self, document_id: str) -> Dict:
-        """Search for a specific document by its ID using the indexed field"""
-        try:
-            # Use scroll to find document by document_id
-            results = self.client.scroll(
-                collection_name=self.collection_name,
-                scroll_filter=models.Filter(
-                    must=[
-                        models.FieldCondition(
-                            key="document_id",
-                            match=models.MatchValue(value=document_id)
-                        )
-                    ]
-                ),
-                limit=1
-            )
-            
-            if results[0]:  # results is a tuple (points, next_page_offset)
-                hit = results[0][0]  # Get first point
-                return {
-                    "text": hit.payload["content"],  # Use content field
-                    "document_id": hit.payload.get("document_id"),
-                    # Include any additional metadata fields
-                    **{k: v for k, v in hit.payload.items() if k not in ["content", "document_id"]}
-                }
-            else:
-                return None
-                
-        except Exception as e:
-            print(f"Error searching by document ID: {e}")
-            return None
-    
-    def search_by_content(self, content_query: str, limit: int = 5) -> List[Dict]:
-        """Search for documents by content using the TEXT index"""
-        try:
-            # Use scroll with text search filter
-            results = self.client.scroll(
-                collection_name=self.collection_name,
-                scroll_filter=models.Filter(
-                    must=[
-                        models.FieldCondition(
-                            key="content",
-                            match=models.MatchText(text=content_query)
-                        )
-                    ]
-                ),
-                limit=limit
-            )
-            
-            # Return results
-            return [
-                {
-                    "text": hit.payload["content"],  # Use content field
-                    "document_id": hit.payload.get("document_id"),
-                    # Include any additional metadata fields
-                    **{k: v for k, v in hit.payload.items() if k not in ["content", "document_id"]}
-                }
-                for hit in results[0]  # results[0] contains the points
-            ]
-            
-        except Exception as e:
-            print(f"Error searching by content: {e}")
-            return []
-    
     def get_collection_info(self) -> Dict:
         """Get information about the collection"""
         try: