File size: 4,520 Bytes
711ee65
 
 
 
 
 
 
 
 
 
 
 
 
 
790fa45
 
b0e8b7f
 
711ee65
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
790fa45
 
711ee65
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
import os
from typing import List
from chainlit.types import AskFileResponse
from aimakerspace.text_utils import CharacterTextSplitter, TextFileLoader, PDFLoader
from aimakerspace.openai_utils.prompts import (
    UserRolePrompt,
    SystemRolePrompt,
    AssistantRolePrompt,
)
from aimakerspace.openai_utils.embedding import EmbeddingModel
from aimakerspace.vectordatabase import VectorDatabase
from aimakerspace.openai_utils.chatmodel import ChatOpenAI
import chainlit as cl

# Ensure OpenAI API key is set in environment variables
if not os.getenv("OPENAI_API_KEY"):
    raise ValueError("OPENAI_API_KEY environment variable is not set")

system_template = """\
Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer."""
system_role_prompt = SystemRolePrompt(system_template)

user_prompt_template = """\
Context:
{context}

Question:
{question}
"""
user_role_prompt = UserRolePrompt(user_prompt_template)

class RetrievalAugmentedQAPipeline:
    def __init__(self, llm: ChatOpenAI(), vector_db_retriever: VectorDatabase) -> None:
        self.llm = llm
        self.vector_db_retriever = vector_db_retriever

    async def arun_pipeline(self, user_query: str):
        context_list = self.vector_db_retriever.search_by_text(user_query, k=4)

        context_prompt = ""
        for context in context_list:
            context_prompt += context[0] + "\n"

        formatted_system_prompt = system_role_prompt.create_message()

        formatted_user_prompt = user_role_prompt.create_message(question=user_query, context=context_prompt)

        async def generate_response():
            async for chunk in self.llm.astream([formatted_system_prompt, formatted_user_prompt]):
                yield chunk

        return {"response": generate_response(), "context": context_list}

text_splitter = CharacterTextSplitter()


def process_file(file: AskFileResponse):
    import tempfile
    import shutil
    
    print(f"Processing file: {file.name}")
    
    # Create a temporary file with the correct extension
    suffix = f".{file.name.split('.')[-1]}"
    with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as temp_file:
        # Copy the uploaded file content to the temporary file
        shutil.copyfile(file.path, temp_file.name)
        print(f"Created temporary file at: {temp_file.name}")
        
        # Create appropriate loader
        if file.name.lower().endswith('.pdf'):
            loader = PDFLoader(temp_file.name)
        else:
            loader = TextFileLoader(temp_file.name)
            
        try:
            # Load and process the documents
            documents = loader.load_documents()
            texts = text_splitter.split_texts(documents)
            return texts
        finally:
            # Clean up the temporary file
            try:
                os.unlink(temp_file.name)
            except Exception as e:
                print(f"Error cleaning up temporary file: {e}")


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

    # Wait for the user to upload a file
    while files == None:
        files = await cl.AskFileMessage(
            content="Please upload a Text or PDF file to begin!",
            accept=["text/plain", "application/pdf"],
            max_size_mb=2,
            timeout=180,
        ).send()

    file = files[0]

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

    # load the file
    texts = process_file(file)

    print(f"Processing {len(texts)} text chunks")

    # Create a dict vector store
    vector_db = VectorDatabase()
    vector_db = await vector_db.abuild_from_list(texts)
    
    # Initialize ChatOpenAI (API key will be automatically picked up from environment variable)
    chat_openai = ChatOpenAI()

    # Create a chain
    retrieval_augmented_qa_pipeline = RetrievalAugmentedQAPipeline(
        vector_db_retriever=vector_db,
        llm=chat_openai
    )
    
    # Let the user know that the system is ready
    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
    await msg.update()

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


@cl.on_message
async def main(message):
    chain = cl.user_session.get("chain")

    msg = cl.Message(content="")
    result = await chain.arun_pipeline(message.content)

    async for stream_resp in result["response"]:
        await msg.stream_token(stream_resp)

    await msg.send()