Update app.py

app.py

@@ -2,10 +2,10 @@ import streamlit as st
 import pandas as pd
 import os
 from dotenv import load_dotenv
-from llama_index.core import Settings, VectorStoreIndex, SimpleDirectoryReader
 from llama_index.readers.file.paged_csv.base import PagedCSVReader
-from llama_index.embeddings.openai import OpenAIEmbedding
+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.document_loaders.csv_loader import CSVLoader
@@ -15,9 +15,9 @@ from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_openai import OpenAIEmbeddings, ChatOpenAI
 import faiss
-import tempfile
 
 # Load environment variables
+load_dotenv()
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
 
 # Global settings for LlamaIndex
@@ -37,29 +37,23 @@ if uploaded_file:
         st.write("Preview of uploaded data:")
         st.dataframe(data)
 
-        # Tabs
-        tab1, tab2 = st.tabs(["Chat w CSV using LangChain", "Chat w CSV using LlamaIndex"])
+        # Tabs for LangChain and LlamaIndex
+        tab1, tab2 = st.tabs(["LangChain", "LlamaIndex"])
 
         # LangChain Tab
         with tab1:
             st.subheader("LangChain Query")
             try:
-                # Write uploaded file to a temporary file for LangChain
-                with tempfile.NamedTemporaryFile(delete=False, suffix=".csv", mode="w") as temp_file:
-                    # Save the DataFrame content to the temporary file
-                    data.to_csv(temp_file.name, index=False)
-                    temp_file_path = temp_file.name
-
-                # Use CSVLoader with the temporary file path
-                loader = CSVLoader(file_path=temp_file_path)
+                # Use CSVLoader with the uploaded DataFrame
+                loader = CSVLoader(data=data)
                 docs = loader.load_and_split()
 
-                # Preview the first document
+                # Preview the first document chunk
                 if docs:
                     st.write("Preview of a document chunk (LangChain):")
                     st.text(docs[0].page_content)
 
-                # LangChain FAISS VectorStore
+                # Create FAISS VectorStore
                 langchain_index = faiss.IndexFlatL2(EMBED_DIMENSION)
                 langchain_vector_store = LangChainFAISS(
                     embedding_function=OpenAIEmbeddings(),
@@ -82,37 +76,23 @@ 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 for LangChain
+                # Query input
                 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']}")
-
             except Exception as e:
                 st.error(f"Error processing with LangChain: {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)
 
         # LlamaIndex Tab
         with tab2:
             st.subheader("LlamaIndex Query")
             try:
-                # Write uploaded file to a temporary file for LlamaIndex
-                with tempfile.NamedTemporaryFile(delete=False, suffix=".csv", mode="w") as temp_file:
-                    data.to_csv(temp_file.name, index=False)
-                    temp_file_path = temp_file.name
-
-                # Use PagedCSVReader for LlamaIndex
+                # Use PagedCSVReader directly on the uploaded DataFrame
                 csv_reader = PagedCSVReader()
-                reader = SimpleDirectoryReader(
-                    input_files=[temp_file_path],
-                    file_extractor={".csv": csv_reader},
-                )
-                docs = reader.load_data()
+                docs = csv_reader.load_from_dataframe(data)
 
-                # Preview the first document
+                # Preview the first document chunk
                 if docs:
                     st.write("Preview of a document chunk (LlamaIndex):")
                     st.text(docs[0].text)
@@ -129,16 +109,13 @@ if uploaded_file:
                 llama_index = VectorStoreIndex(nodes)
                 query_engine = llama_index.as_query_engine(similarity_top_k=3)
 
-                # Query input for LlamaIndex
+                # 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}")
             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)
+
     except Exception as e:
         st.error(f"Error reading uploaded file: {e}")