Update tools.py

tools.py

@@ -1,3 +1,4 @@
+```python
 from langchain_core.tools import tool
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import FAISS
@@ -17,73 +18,56 @@ load_dotenv()
 VECTORSTORE_DIR = "data/vectorstore"
 os.makedirs(VECTORSTORE_DIR, exist_ok=True)
 
-retriever = None
 
-
-def load_retriever():
-    """Load FAISS retriever from disk if available."""
-    global retriever
-
-    try:
-        embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
-        index_path = os.path.join(VECTORSTORE_DIR, "index.faiss")
-
-        if os.path.exists(index_path):
-            vectorstore = FAISS.load_local(
-                VECTORSTORE_DIR,
-                embeddings,
-                allow_dangerous_deserialization=True,
-            )
-            retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
-            print("✅ Retriever loaded successfully")
-        else:
-            print("⚠️ No vectorstore found yet")
-
-    except Exception as e:
-        print("❌ Retriever load error:", e)
-
-
-# Load on startup
-load_retriever()
-
-
-def build_vectorstore(path: str):
-    loader = PyPDFLoader(path)
-    docs = loader.load()
+# ==============================
+# VECTOR STORE CREATION
+# ==============================
+def build_vectorstore(file_path: str):
+    loader = PyPDFLoader(file_path)
+    documents = loader.load()
 
     splitter = RecursiveCharacterTextSplitter(
         chunk_size=500,
         chunk_overlap=100
     )
 
-    chunks = splitter.split_documents(docs)
-    embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+    chunks = splitter.split_documents(documents)
 
+    embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
     vectorstore = FAISS.from_documents(chunks, embeddings)
-    vectorstore.save_local(VECTORSTORE_DIR)
 
+    vectorstore.save_local(VECTORSTORE_DIR)
     return vectorstore
 
 
-def update_retriever(path: str):
-    global retriever
-    retriever = build_vectorstore(path).as_retriever(search_kwargs={"k": 4})
+def update_retriever(file_path: str):
+    """Rebuild vectorstore when a new document is uploaded."""
+    build_vectorstore(file_path)
 
 
 # ==============================
-# RAG TOOL
+# RAG TOOL (HF SAFE)
 # ==============================
 def create_rag_tool():
 
     @tool
     def rag_search(query: str) -> str:
-        """Retrieve relevant context from uploaded documents."""
+        """
+        Retrieve relevant information from uploaded documents.
+        """
 
-        global retriever
+        if not os.path.exists(os.path.join(VECTORSTORE_DIR, "index.faiss")):
+            return "No document has been uploaded yet."
 
-        if retriever is None:
-            return "No document uploaded yet."
+        embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+
+        vectorstore = FAISS.load_local(
+            VECTORSTORE_DIR,
+            embeddings,
+            allow_dangerous_deserialization=True
+        )
 
+        retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
         docs = retriever.invoke(query)
 
         if not docs:
@@ -94,9 +78,9 @@ def create_rag_tool():
     return rag_search
 
 
-# -----------------------------
-# External tools (safe)
-# -----------------------------
+# ==============================
+# EXTRA TOOLS
+# ==============================
 
 @tool
 def wikipedia_search(query: str) -> dict:
@@ -122,4 +106,5 @@ def tavily_search(query: str) -> dict:
     try:
         return {"results": TavilySearchResults(max_results=5).run(query)}
     except Exception as e:
-        return {"error": str(e)}
+        return {"error": str(e)}
+```