app.py

"""
IMPORTS HERE
"""
import chainlit as cl
from qdrant_client import QdrantClient
from qdrant_client.http.models import Distance, VectorParams

from langchain_qdrant import QdrantVectorStore

from operator import itemgetter
from langchain_core.runnables.passthrough import RunnablePassthrough
from langchain_core.runnables.config import RunnableConfig
import uuid
from prompts import chat_prompt 
from handle_files import split_file
from models import chat_model, cached_embedder

"""
GLOBAL CODE HERE
"""

# Typical QDrant Client Set-up
collection_name = f"pdf_to_parse_{uuid.uuid4()}"
client = QdrantClient(":memory:")
client.create_collection(
    collection_name=collection_name,
    vectors_config=VectorParams(size=1536, distance=Distance.COSINE),
)

# Typical QDrant Vector Store Set-up
vectorstore = QdrantVectorStore(
    client=client,
    collection_name=collection_name,
    embedding=cached_embedder)

### On Chat Start (Session Start) Section ###
@cl.on_chat_start
async def on_chat_start():
    """ SESSION SPECIFIC CODE HERE """
    files = None

    # Wait for the user to upload a file
    while files == None:
        files = await cl.AskFileMessage(
            content="Please upload a PDF File file to begin!",
            accept=["application/pdf"],
            max_size_mb=20,
            timeout=180,
        ).send()

    file = files[0]


    msg = cl.Message(
        content=f"Processing `{file.name}`..."
    )

    await msg.send()
   
    docs = split_file(file)
    vectorstore.add_documents(docs)

    retriever = vectorstore.as_retriever(search_type="mmr", search_kwargs={"k": 15})
    retrieval_augmented_qa_chain = (
        {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
        | RunnablePassthrough.assign(context=itemgetter("context"))
        | chat_prompt | chat_model
    )
    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
    await msg.send()

    cl.user_session.set("chain", retrieval_augmented_qa_chain)

# ### Rename Chains ###
@cl.author_rename
def rename(orig_author: str):
    """ RENAME CODE HERE """
    rename_dict = {"ChatOpenAI": "the Generator ...", "VectorStoreRetriever" : "the Retriever"}
    return rename_dict.get(orig_author, orig_author)


### On Message Section ###
@cl.on_message
async def main(message: cl.Message):
    """
    MESSAGE CODE HERE
    """
    chain = cl.user_session.get("chain")

    msg = cl.Message(content="")

    async for stream_response in chain.astream(
        {"question":message.content},
        config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()])
    ):
        await msg.stream_token(stream_response.content)

    await msg.send()