Update app.py

app.py

@@ -8,7 +8,6 @@ from llama_index.core import Settings, VectorStoreIndex
 from llama_index.llms.openai import OpenAI
 from llama_index.embeddings.openai import OpenAIEmbedding
 from llama_index.vector_stores.faiss import FaissVectorStore
-from llama_index.core.ingestion import IngestionPipeline
 from langchain_community.vectorstores import FAISS as LangChainFAISS
 from langchain_community.docstore.in_memory import InMemoryDocstore
 from langchain.chains import create_retrieval_chain
@@ -18,7 +17,6 @@ from langchain_openai import OpenAIEmbeddings, ChatOpenAI
 from langchain_core.documents import Document  
 import faiss
 import tempfile
-from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 # Load environment variables
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
@@ -62,17 +60,14 @@ if uploaded_file:
             st.subheader("LangChain Query")
 
             try:
-                # ✅ Convert CSV rows into LangChain Document objects with chunking
+                # ✅ Store each row as a single document
                 st.write("Processing CSV with a custom loader...")
-                text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=90)
                 documents = []
 
                 for _, row in data.iterrows():
-                    content = "\n".join([f"{col}: {row[col]}" for col in data.columns])
-                    chunks = text_splitter.split_text(content)
-                    for chunk in chunks:
-                        doc = Document(page_content=chunk)
-                        documents.append(doc)
+                    content = " | ".join([f"{col}: {row[col]}" for col in data.columns])  # ✅ Store entire row as a document
+                    doc = Document(page_content=content)
+                    documents.append(doc)
 
                 # ✅ Create FAISS VectorStore
                 st.write(f"✅ Initializing FAISS with dimension: {faiss_dimension}")
@@ -96,31 +91,21 @@ if uploaded_file:
                     st.error(f"Error adding documents to FAISS: {e}")
 
                 # ✅ Limit number of retrieved documents
-                retriever = langchain_vector_store.as_retriever(search_kwargs={"k": 5})
-
-                # ✅ Create LangChain Query Execution Pipeline
-                system_prompt = (
-                    "You are an assistant for question-answering tasks. "
-                    "Use the following pieces of retrieved context to answer "
-                    "the question. 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)
+                retriever = langchain_vector_store.as_retriever(search_kwargs={"k": 15}) 
 
                 # ✅ Query Processing
                 query = st.text_input("Ask a question about your data (LangChain):")
 
                 if query:
                     try:
-                        retrieved_context = "\n\n".join([doc.page_content for doc in retriever.get_relevant_documents(query)])
+                        retrieved_docs = retriever.get_relevant_documents(query)
+                        retrieved_context = "\n\n".join([doc.page_content for doc in retrieved_docs])
                         retrieved_context = retrieved_context[:3000]  
 
-                        # ✅ Ensure that we use the retrieved context
+                        # ✅ Show retrieved context for debugging
+                        st.write("🔍 **Retrieved Context Preview:**")
+                        st.text(retrieved_context)
+
                         system_prompt = (
                             "You are an assistant for question-answering tasks. "
                             "Use the following pieces of retrieved context to answer "
@@ -133,13 +118,9 @@ if uploaded_file:
                     except Exception as e:
                         error_message = traceback.format_exc()
                         st.error(f"Error processing query: {e}")
-                        st.text(error_message)  
+                        st.text(error_message)
 
             except Exception as e:
                 error_message = traceback.format_exc()
                 st.error(f"Error processing with LangChain: {e}")
-                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)  # 
+                st.text(error_message)