Update rag_tool.py

rag_tool.py

@@ -81,25 +81,22 @@ class RAGTool(Tool):
         
     def _setup_vector_store(self):
         """Set up the vector store with documents if it doesn't exist"""
-        # Check if we need to create a new vector store
-        if not os.path.exists(os.path.join(self.persist_directory, "index.faiss")) and \
-           not os.path.exists(os.path.join(self.persist_directory, "chroma")):
-            # Check if documents path exists
-            if not os.path.exists(self.documents_path):
-                print(f"Warning: Documents path {self.documents_path} does not exist.")
-                return
-            
-            # Load and process documents
-            documents = self._load_documents()
-            if not documents:
-                print("No documents loaded. Vector store not created.")
-                return
-            
-            # Create the vector store
-            self._create_vector_store(documents)
-        else:
-            print(f"Vector store already exists at {self.persist_directory}")
-            self._load_vector_store()
+        # Always try to create directories if they don't exist
+        os.makedirs(self.persist_directory, exist_ok=True)
+        
+        # Check if documents path exists
+        if not os.path.exists(self.documents_path):
+            print(f"Warning: Documents path {self.documents_path} does not exist.")
+            return
+        
+        # Force creation of vector store from documents
+        documents = self._load_documents()
+        if not documents:
+            print("No documents loaded. Vector store not created.")
+            return
+        
+        # Create the vector store
+        self._create_vector_store(documents)
     
     def _get_embeddings(self):
         """Get embedding model based on configuration"""
@@ -225,17 +222,20 @@ class RAGTool(Tool):
                 print("No documents available. Cannot create vector store.")
                 self.vector_store = None
 
-    def forward(self, query: str, top_k: int = 3) -> str:
+    def forward(self, query: str, top_k: int = None) -> str:
         """
         Retrieve relevant documents based on the query.
         
         Args:
             query: The search query
-            top_k: Number of results to return
+            top_k: Number of results to return (default: 3)
             
         Returns:
             String with formatted search results
         """
+        # Set default value if None
+        if top_k is None:
+            top_k = 3
         if not hasattr(self, 'vector_store') or self.vector_store is None:
             return "Vector store is not initialized. Please check your configuration."