Update pipeline.py

pipeline.py

@@ -188,9 +188,6 @@ def classify_query(query: str) -> str:
 ################################################################################
 
 def build_or_load_vectorstore(csv_path: str, store_dir: str) -> FAISS:
-    """
-    Builds or loads a FAISS vector store for CSV documents containing 'Question' and 'Answers'.
-    """
     try:
         if os.path.exists(store_dir):
             print(f"DEBUG: Found existing FAISS store at '{store_dir}'. Loading...")
@@ -202,22 +199,18 @@ def build_or_load_vectorstore(csv_path: str, store_dir: str) -> FAISS:
             df = pd.read_csv(csv_path)
             df = df.loc[:, ~df.columns.str.contains('^Unnamed')]
             df.columns = df.columns.str.strip()
-            
-            # Fix possible column name variations
             if "Answer" in df.columns:
                 df.rename(columns={"Answer": "Answers"}, inplace=True)
             if "Question" not in df.columns and "Question " in df.columns:
                 df.rename(columns={"Question ": "Question"}, inplace=True)
             if "Question" not in df.columns or "Answers" not in df.columns:
                 raise ValueError("CSV must have 'Question' and 'Answers' columns.")
-            
             docs = []
             for _, row in df.iterrows():
                 q = str(row["Question"])
                 ans = str(row["Answers"])
                 doc = Document(page_content=ans, metadata={"question": q})
                 docs.append(doc)
-            
             embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/multi-qa-mpnet-base-dot-v1")
             vectorstore = FAISS.from_documents(docs, embedding=embeddings)
             vectorstore.save_local(store_dir)
@@ -227,11 +220,11 @@ def build_or_load_vectorstore(csv_path: str, store_dir: str) -> FAISS:
         raise RuntimeError(f"Error building/loading vector store: {str(e)}")
 
 def build_rag_chain(vectorstore: FAISS) -> RetrievalQA:
-    """Build RAG chain using the Gemini LLM."""
+    """Build RAG chain using the Gemini LLM directly without a custom class."""
     try:
         retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 3})
         chain = RetrievalQA.from_chain_type(
-            llm=gemini_llm,
+            llm=gemini_llm,  # Directly use the ChatGoogleGenerativeAI instance
             chain_type="stuff",
             retriever=retriever,
             return_source_documents=True
@@ -239,7 +232,6 @@ def build_rag_chain(vectorstore: FAISS) -> RetrievalQA:
         return chain
     except Exception as e:
         raise RuntimeError(f"Error building RAG chain: {str(e)}")
-
 ################################################################################
 # Web Search Caching: Separate FAISS Vector Store
 ################################################################################