Update app.py

app.py

@@ -14,6 +14,7 @@ from langchain.chains import create_retrieval_chain
 from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+from langchain_core.documents import Document  # ✅ FIX: Import LangChain Document
 import faiss
 import tempfile
 
@@ -44,7 +45,7 @@ if uploaded_file:
             data.to_csv(temp_file.name, index=False, encoding="utf-8")
             temp_file.flush()
 
-        # Debugging: Verify the temporary file (Display partially)
+        # Verify the temporary file (Display partial content)
         st.write("Temporary file path:", temp_file_path)
         with open(temp_file_path, "r") as f:
             content = f.read()
@@ -54,35 +55,35 @@ if uploaded_file:
         # Tabs for LangChain and LlamaIndex
         tab1, tab2 = st.tabs(["LangChain", "LlamaIndex"])
 
-        # LangChain Tab with Proper FAISS Initialization
+        # ✅ LangChain Processing with Proper Document Format
         with tab1:
             st.subheader("LangChain Query")
+
             try:
-                # Custom preprocessing: Split CSV rows into smaller chunks
+                # ✅ Convert CSV rows into LangChain Document objects (Fix for `dict` error)
                 st.write("Processing CSV with a custom loader...")
                 documents = []
                 for _, row in data.iterrows():
                     content = "\n".join([f"{col}: {row[col]}" for col in data.columns])
-                    documents.append({"page_content": content})
-
-                # Debugging: Preview loaded documents
-                #st.write("Successfully processed documents:")
-                #if documents:
-                #    st.text(documents[0]["page_content"])
+                    doc = Document(page_content=content)  # Convert to Document object
+                    documents.append(doc)  # Append to list
 
-                # Create FAISS VectorStore with proper arguments
+                # ✅ Create FAISS VectorStore with proper arguments
                 langchain_index = faiss.IndexFlatL2(EMBED_DIMENSION)
-                docstore = InMemoryDocstore()  # Create an in-memory docstore
+                docstore = InMemoryDocstore()  # In-memory storage for documents
                 index_to_docstore_id = {}  # Mapping of index to document ID
+
                 langchain_vector_store = LangChainFAISS(
                     embedding_function=OpenAIEmbeddings(),
                     index=langchain_index,
                     docstore=docstore,
                     index_to_docstore_id=index_to_docstore_id,
                 )
+
+                # ✅ Add properly formatted documents to FAISS
                 langchain_vector_store.add_documents(documents)
 
-                # LangChain Retrieval Chain
+                # ✅ LangChain Retrieval Chain
                 retriever = langchain_vector_store.as_retriever()
                 system_prompt = (
                     "You are an assistant for question-answering tasks. "
@@ -97,47 +98,56 @@ if uploaded_file:
                 question_answer_chain = create_stuff_documents_chain(ChatOpenAI(model="gpt-4o"), prompt)
                 langchain_rag_chain = create_retrieval_chain(retriever, question_answer_chain)
 
-                # Query input
+                # ✅ Query Input Field for LangChain
                 query = st.text_input("Ask a question about your data (LangChain):")
+
                 if query:
-                    answer = langchain_rag_chain.invoke({"input": query})
-                    st.write(f"Answer: {answer['answer']}")
+                    try:
+                        st.write("Processing your question...")
+                        answer = langchain_rag_chain.invoke({"input": query})
+                        st.write(f"**Answer:** {answer['answer']}")
+                    except Exception as e:
+                        st.error(f"Error processing query: {e}")
+
             except Exception as e:
                 st.error(f"Error processing with LangChain: {e}")
 
-        # LlamaIndex Tab
+        # ✅ LlamaIndex Processing
         with tab2:
             st.subheader("LlamaIndex Query")
+
             try:
-                # Use PagedCSVReader directly on the uploaded file
+                # Use PagedCSVReader to load CSV
                 st.write("Loading file with LlamaIndex PagedCSVReader...")
                 csv_reader = PagedCSVReader()
                 docs = csv_reader.load_from_file(temp_file_path)
 
-                # Debugging: Preview loaded documents
-                st.write("Successfully loaded documents:")
-                if docs:
-                    st.text(docs[0].text)
-
-                # Initialize FAISS Vector Store
+                # ✅ Create FAISS Vector Store
                 llama_faiss_index = faiss.IndexFlatL2(EMBED_DIMENSION)
                 llama_vector_store = FaissVectorStore(faiss_index=llama_faiss_index)
 
-                # Create the ingestion pipeline and process the data
+                # ✅ Create ingestion pipeline and process data
                 pipeline = IngestionPipeline(vector_store=llama_vector_store, documents=docs)
                 nodes = pipeline.run()
 
-                # Create a query engine
+                # ✅ Create a query engine
                 llama_index = VectorStoreIndex(nodes)
                 query_engine = llama_index.as_query_engine(similarity_top_k=3)
 
-                # Query input
-                query = st.text_input("Ask a question about your data (LlamaIndex):")
-                if query:
-                    response = query_engine.query(query)
-                    st.write(f"Answer: {response.response}")
+                # ✅ Query Input Field for LlamaIndex
+                query_llama = st.text_input("Ask a question about your data (LlamaIndex):")
+
+                if query_llama:
+                    try:
+                        st.write("Processing your question...")
+                        response = query_engine.query(query_llama)
+                        st.write(f"**Answer:** {response.response}")
+                    except Exception as e:
+                        st.error(f"Error processing query: {e}")
+
             except Exception as e:
                 st.error(f"Error processing with LlamaIndex: {e}")
+
             finally:
                 # Clean up the temporary file
                 if 'temp_file_path' in locals() and os.path.exists(temp_file_path):