app.py

import os
from getpass import getpass
import streamlit as st
from dotenv import load_dotenv
from openai.embeddings_utils import OpenAIEmbeddings
from openai import OpenAI
from pinecone import PineconeClient, VectorStore
from faiss import IndexFlatL2
from llama_index import VectorStoreIndex, VectorIndexRetriever
from llama_index.node_parser import SemanticSplitterNodeParser
from llama_index.embeddings import OpenAIEmbedding
from llama_index.ingestion import IngestionPipeline
from llama_index.query_engine import RetrieverQueryEngine
from llama_index.memory import ConversationBufferMemory
from llama_index.chains import ConversationalRetrievalChain
from llama_index.prompts import user_template, bot_template, css

# Load environment variables
load_dotenv()
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
pinecone_client = PineconeClient(api_key=pinecone_api_key)
pinecone_index = pinecone_client.Index(index_name)
vector_store = VectorStore(pinecone_index=pinecone_index)

# Initialize LlamaIndex components
embed_model = OpenAIEmbedding(api_key=openai_api_key)
pipeline = IngestionPipeline(
    transformations=[
        SemanticSplitterNodeParser(
            buffer_size=1,
            breakpoint_percentile_threshold=95,
            embed_model=embed_model,
        ),
        embed_model,
    ],
)
vector_index = VectorStoreIndex.from_vector_store(vector_store=vector_store)
retriever = VectorIndexRetriever(index=vector_index, similarity_top_k=5)
query_engine = RetrieverQueryEngine(retriever=retriever)

def get_vectorstore(text_chunks):
    embeddings = OpenAIEmbeddings()
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

def get_conversation_chain(vectorstore):
    llm = OpenAI()
    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=vectorstore.as_retriever(),
        memory=memory
    )
    return conversation_chain

def handle_userinput(user_question):
    response = st.session_state.conversation({'question': user_question})
    st.session_state.chat_history = response['chat_history']
    
    for i, message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)

def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with Annual Reports", page_icon=":books:")
    st.write(css, unsafe_allow_html=True)

    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header("Chat with Annual Report Documents")
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

if __name__ == "__main__":
    main()