app.py

# You can find this code for Chainlit python streaming here (https://docs.chainlit.io/concepts/streaming/python)

# OpenAI Chat completion
import os
from openai import AsyncOpenAI  # importing openai for API usage
import chainlit as cl  # importing chainlit for our app
from chainlit.prompt import Prompt, PromptMessage  # importing prompt tools
from chainlit.playground.providers import ChatOpenAI  # importing ChatOpenAI tools
from dotenv import load_dotenv
from src.retrieval_lib import initialize_index, load_pdf_to_text, split_text, load_text_to_index, query_index, create_answer_prompt, generate_answer

load_dotenv()

retriever = initialize_index()

@cl.on_chat_start  # marks a function that will be executed at the start of a user session
async def start_chat():
    settings = {
        "model": "gpt-3.5-turbo",
        "temperature": 0,
        "max_tokens": 500,
        "top_p": 1,
        "frequency_penalty": 0,
        "presence_penalty": 0,
    }
    cl.user_session.set("settings", settings)


@cl.on_message  # marks a function that should be run each time the chatbot receives a message from a user
async def main(message: cl.Message):
    settings = cl.user_session.get("settings")

    client = AsyncOpenAI()

    print(message.content)

    # prompt = Prompt(
    #    provider=ChatOpenAI.id,
    #    messages=[
    #        PromptMessage(
    #            role="system",
    #            template=system_template,
    #            formatted=system_template,
    #        ),
    #        PromptMessage(
    #            role="user",
    #            template=user_template,
    #            formatted=user_template.format(input=message.content),
    #        ),
    #    ],
    #    inputs={"input": message.content},
    #    settings=settings,
    #)

    #print([m.to_openai() for m in prompt.messages])

    query = message.content
    # query = "what is the reason for the lawsuit"
    retrieved_docs = query_index(retriever, query)
    print("retrieved_docs: \n", len(retrieved_docs))
    answer_prompt = create_answer_prompt()
    print("answer_prompt: \n", answer_prompt)
    result = generate_answer(retriever, answer_prompt, query)
    print("result: \n", result["response"].content)

    msg = cl.Message(content="")

    # Call OpenAI
    #async for stream_resp in await client.chat.completions.create(
    #    messages=[m.to_openai() for m in prompt.messages], stream=True, **settings
    #):
    #    token = stream_resp.choices[0].delta.content
    #    if not token:
    #        token = ""
    #    await msg.stream_token(token)

    # Update the prompt object with the completion
    #prompt.completion = msg.content
    #msg.prompt = prompt
    msg.content = result["response"].content

    # Send and close the message stream
    await msg.send()