File size: 2,709 Bytes
1e2602b
 
 
 
f119af7
31f3de1
 
8669df3
31f3de1
2d7499f
31f3de1
 
 
 
2d7499f
8669df3
 
31f3de1
1e2602b
 
 
2d7499f
31f3de1
 
 
 
 
 
 
 
 
 
 
 
 
 
1e2602b
 
 
 
31f3de1
1e2602b
31f3de1
 
 
 
 
 
 
 
 
 
 
8669df3
31f3de1
8669df3
31f3de1
 
 
8669df3
2d7499f
31f3de1
8669df3
31f3de1
 
 
 
 
 
 
b29e219
31f3de1
 
 
 
b29e219
 
 
 
 
 
1e2602b
 
 
 
 
 
31f3de1
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99

"""
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()