Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 import pandas as pd
 import os
+import traceback
 from dotenv import load_dotenv
 from llama_index.readers.file.paged_csv.base import PagedCSVReader
 from llama_index.core import Settings, VectorStoreIndex
@@ -14,14 +15,18 @@ 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
+from langchain_core.documents import Document  
 import faiss
 import tempfile
 
 # Load environment variables
-load_dotenv()
+
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
 
+# Check OpenAI API Key
+if not os.getenv("OPENAI_API_KEY"):
+    st.error("⚠️ OpenAI API Key is missing! Please check your .env file or environment variables.")
+
 # Global settings for LlamaIndex
 EMBED_DIMENSION = 512
 Settings.llm = OpenAI(model="gpt-4o")
@@ -45,7 +50,7 @@ if uploaded_file:
             data.to_csv(temp_file.name, index=False, encoding="utf-8")
             temp_file.flush()
 
-        # Verify the temporary file (Display partial content)
+        # Debugging: 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()
@@ -55,23 +60,28 @@ if uploaded_file:
         # Tabs for LangChain and LlamaIndex
         tab1, tab2 = st.tabs(["LangChain", "LlamaIndex"])
 
-        # ✅ LangChain Processing with Proper Document Format
+        # ✅ LangChain Processing
         with tab1:
             st.subheader("LangChain Query")
 
             try:
-                # ✅ Convert CSV rows into LangChain Document objects (Fix for `dict` error)
+                # ✅ Convert CSV rows into LangChain Document objects
                 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])
-                    doc = Document(page_content=content)  # Convert to Document object
-                    documents.append(doc)  # Append to list
+                    doc = Document(page_content=content) 
+                    documents.append(doc)
+
+                # Print a sample document
+                if documents:
+                    st.write("Sample processed document (LangChain):")
+                    st.text(documents[0].page_content)
 
-                # ✅ Create FAISS VectorStore with proper arguments
+                # ✅ Create FAISS VectorStore
                 langchain_index = faiss.IndexFlatL2(EMBED_DIMENSION)
-                docstore = InMemoryDocstore()  # In-memory storage for documents
-                index_to_docstore_id = {}  # Mapping of index to document ID
+                docstore = InMemoryDocstore()
+                index_to_docstore_id = {}
 
                 langchain_vector_store = LangChainFAISS(
                     embedding_function=OpenAIEmbeddings(),
@@ -82,23 +92,9 @@ if uploaded_file:
 
                 # ✅ Add properly formatted documents to FAISS
                 langchain_vector_store.add_documents(documents)
+                st.write("Documents successfully added to FAISS VectorStore.")
 
-                # ✅ LangChain Retrieval Chain
-                retriever = langchain_vector_store.as_retriever()
-                system_prompt = (
-                    "You are an assistant for question-answering tasks. "
-                    "Use the following pieces of retrieved context to answer "
-                    "the question. If you don't know the answer, say that you "
-                    "don't know. Use three sentences maximum and keep the "
-                    "answer concise.\n\n{context}"
-                )
-                prompt = ChatPromptTemplate.from_messages(
-                    [("system", system_prompt), ("human", "{input}")]
-                )
-                question_answer_chain = create_stuff_documents_chain(ChatOpenAI(model="gpt-4o"), prompt)
-                langchain_rag_chain = create_retrieval_chain(retriever, question_answer_chain)
-
-                # ✅ Query Input Field for LangChain
+                # ✅ Query Processing
                 query = st.text_input("Ask a question about your data (LangChain):")
 
                 if query:
@@ -107,51 +103,16 @@ if uploaded_file:
                         answer = langchain_rag_chain.invoke({"input": query})
                         st.write(f"**Answer:** {answer['answer']}")
                     except Exception as e:
+                        error_message = traceback.format_exc()
                         st.error(f"Error processing query: {e}")
+                        st.text(error_message) 
 
             except Exception as e:
+                error_message = traceback.format_exc()
                 st.error(f"Error processing with LangChain: {e}")
-
-        # ✅ LlamaIndex Processing
-        with tab2:
-            st.subheader("LlamaIndex Query")
-
-            try:
-                # Use PagedCSVReader to load CSV
-                st.write("Loading file with LlamaIndex PagedCSVReader...")
-                csv_reader = PagedCSVReader()
-                docs = csv_reader.load_from_file(temp_file_path)
-
-                # ✅ Create FAISS Vector Store
-                llama_faiss_index = faiss.IndexFlatL2(EMBED_DIMENSION)
-                llama_vector_store = FaissVectorStore(faiss_index=llama_faiss_index)
-
-                # ✅ Create ingestion pipeline and process data
-                pipeline = IngestionPipeline(vector_store=llama_vector_store, documents=docs)
-                nodes = pipeline.run()
-
-                # ✅ Create a query engine
-                llama_index = VectorStoreIndex(nodes)
-                query_engine = llama_index.as_query_engine(similarity_top_k=3)
-
-                # ✅ 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):
-                    os.remove(temp_file_path)
+                st.text(error_message) 
 
     except Exception as e:
+        error_message = traceback.format_exc()
         st.error(f"Error reading uploaded file: {e}")
+        st.text(error_message)