Update pipeline.py

pipeline.py

@@ -131,24 +131,31 @@ def classify_query(query: str) -> str:
 def build_or_load_vectorstore(csv_path: str, store_dir: str) -> FAISS:
     try:
         if os.path.exists(store_dir):
-            print(f"Loading existing FAISS store from '{store_dir}'")
+            print(f"DEBUG: Found existing FAISS store at '{store_dir}'. Loading...")
             embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/multi-qa-mpnet-base-dot-v1")
-            return FAISS.load_local(store_dir, embeddings)
-        
-        print(f"Building new FAISS store from CSV: {csv_path}")
-        df = pd.read_csv(csv_path)
-        df = df.loc[:, ~df.columns.str.contains('^Unnamed')]
-        df.columns = df.columns.str.strip()
-        
-        docs = [
-            Document(page_content=str(row["Answer"]), metadata={"question": str(row["Question"])})
-            for _, row in df.iterrows()
-        ]
-        
-        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/multi-qa-mpnet-base-dot-v1")
-        vectorstore = FAISS.from_documents(docs, embedding=embeddings)
-        vectorstore.save_local(store_dir)
-        return vectorstore
+            vectorstore = FAISS.load_local(store_dir, embeddings)
+            return vectorstore
+        else:
+            print(f"DEBUG: Building new store from CSV: {csv_path}")
+            df = pd.read_csv(csv_path)
+            df = df.loc[:, ~df.columns.str.contains('^Unnamed')]
+            df.columns = df.columns.str.strip()
+            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)
+            return vectorstore
         
     except Exception as e:
         raise RuntimeError(f"Error building/loading vector store: {str(e)}")