app.py

import os
import streamlit as st
import random
import time

from langchain.chains import RetrievalQA
from langchain.chat_models import ChatOpenAI
from langchain.document_loaders import DataFrameLoader
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma


# Get OpenAI setup
openai_api_key = os.getenv("openai_token")
embedding = OpenAIEmbeddings(openai_api_key=openai_api_key)

# Setup vector database
persist_directory = './chroma_db'
vectordb = Chroma(persist_directory=persist_directory, embedding_function=embedding)

llm_name = "gpt-3.5-turbo"

llm = ChatOpenAI(model_name=llm_name, temperature=0,
                 openai_api_key=openai_api_key)

qa_chain = RetrievalQA.from_chain_type(
    llm,
    retriever=vectordb.as_retriever()
)

question = "production is broken how do I fix it?"

result = qa_chain({"query": question})

print(result['result'])


# Streamed response emulator
def response_generator(prompt):
    response = qa_chain({"query": prompt})['result']   
    
    for word in response.split():
        yield word + " "
        time.sleep(0.05)


st.title("Simple chat")

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# Display chat messages from history on app rerun
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# Accept user input
if prompt := st.chat_input("What is up?"):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)

    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        response = st.write_stream(response_generator(prompt))
    # Add assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": response})