Update app.py

app.py

@@ -1,12 +1,15 @@
 import os
-from getpass import getpass
 import streamlit as st
 from dotenv import load_dotenv
+from pinecone import PineconeClient
 from llama_index.embeddings import OpenAIEmbedding
 from llama_index.ingestion import IngestionPipeline
 from llama_index.query_engine import RetrieverQueryEngine
-from llama_index.core.memory import ConversationBufferMemory
+from llama_index.vector_stores import PineconeVectorStore
+from llama_index.memory import ConversationBufferMemory
 from llama_index.chains import ConversationalRetrievalChain
+from llama_index.node_parser import SemanticSplitterNodeParser
+from llama_index.retrievers import VectorIndexRetriever
 from llama_index.prompts import user_template, bot_template, css
 
 # Load environment variables
@@ -15,14 +18,15 @@ pinecone_api_key = os.getenv("PINECONE_API_KEY")
 openai_api_key = os.getenv("OPENAI_API_KEY")
 index_name = os.getenv("INDEX_NAME")
 
-# Initialize OpenAI and Pinecone clients
-openai.api_key = openai_api_key
+# Initialize OpenAI embedding model
+embed_model = OpenAIEmbedding(api_key=openai_api_key)
+
+# Initialize connection to Pinecone
 pinecone_client = PineconeClient(api_key=pinecone_api_key)
 pinecone_index = pinecone_client.Index(index_name)
-vector_store = VectorStore(pinecone_index=pinecone_index)
+vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
 
-# Initialize LlamaIndex components
-embed_model = OpenAIEmbedding(api_key=openai_api_key)
+# Define the initial pipeline
 pipeline = IngestionPipeline(
  transformations=[
  SemanticSplitterNodeParser(
@@ -33,12 +37,13 @@ pipeline = IngestionPipeline(
  embed_model,
  ],
 )
+
+# Initialize LlamaIndex components
 vector_index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
 retriever = VectorIndexRetriever(index=vector_index, similarity_top_k=5)
 query_engine = RetrieverQueryEngine(retriever=retriever)
 
-
-
+# Function to handle user input and return the query response
 def handle_userinput(user_question):
  response = st.session_state.conversation({'question': user_question})
  st.session_state.chat_history = response['chat_history']
@@ -49,6 +54,7 @@ def handle_userinput(user_question):
  else:
  st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
 
+# Main function to run the Streamlit app
 def main():
  load_dotenv()
  st.set_page_config(page_title="Chat with Annual Reports", page_icon=":books:")