app.py

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyMuPDFLoader

from langchain_community.vectorstores import Qdrant

from langchain_openai import OpenAIEmbeddings

from langchain.retrievers import MultiQueryRetriever

from langchain.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from langchain.schema.runnable.config import RunnableConfig

from operator import itemgetter
from langchain_core.runnables import RunnablePassthrough
from langchain.schema import StrOutputParser

from dotenv import load_dotenv

import os
import chainlit as cl

load_dotenv(os.getenv("OPENAI_API_KEY"))

@cl.on_chat_start
async def init():
    files = None

    # Wait for the user to upload a PDF file
    while files is None:
        files = await cl.AskFileMessage(
            content="Please upload a PDF file to begin!",
            accept=["application/pdf"],
            max_size_mb=100,
            timeout=180,
        ).send()

    file = files[0]  

    msg = cl.Message(content=f"Processing `{file.name}`...")
    await msg.send()      
    
    loader = PyMuPDFLoader(file.path)
    documents = loader.load()     
  
    chunk_size=2000
    chunk_overlap = int(0.1 * chunk_size)
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
    documents = text_splitter.split_documents(documents)
  
    embeddings =  OpenAIEmbeddings(model="text-embedding-3-small")   

    qdrant_vector_store = Qdrant.from_documents(
        documents,
        embeddings,
        location=":memory:",
        collection_name="generic-document-store",
    )

    retriever = qdrant_vector_store.as_retriever()    

    primary_qa_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, streaming=True)
    
    retriever = MultiQueryRetriever.from_llm(retriever=retriever, llm=primary_qa_llm) 

    template = """Answer the question based only on the following context. If you cannot answer the question with the context, please respond with 'I don't know':

    Context:
    {context}

    Question:
    {question}
    """
    prompt = ChatPromptTemplate.from_template(template)    

    runnable = (        
        {"context": itemgetter("question") | retriever, "question": itemgetter("question")}       
        | RunnablePassthrough.assign(context=itemgetter("context"))      
        | prompt | primary_qa_llm | StrOutputParser()
    )     

    cl.user_session.set("runnable", runnable)   
    msg.content = f"`{file.name}` processed. You can now ask questions!"

    await msg.update()


@cl.on_message
async def main(message):
    runnable = cl.user_session.get("runnable")    
    msg = cl.Message(content="")
    async for chunk in runnable.astream(
        {"question": message.content},
        config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
    ):
        await msg.stream_token(chunk) 

    await msg.send()