File size: 4,887 Bytes
86e0637
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
145
146
147
148
149
150
151
152
153
154
155
156
import PyPDF2
from langchain_community.embeddings import OllamaEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import Chroma
from langchain.chains import ConversationalRetrievalChain
from langchain_groq import ChatGroq
from langchain.memory import ChatMessageHistory, ConversationBufferMemory
import chainlit as cl
from chainlit.input_widget import Select
import os


@cl.cache
def get_memory():
    # Initialize message history for conversation
    message_history = ChatMessageHistory()
    
    # Memory for conversational context
    memory = ConversationBufferMemory(
        memory_key="chat_history",
        output_key="answer",
        chat_memory=message_history,
        return_messages=True,
    )
    return memory

@cl.on_chat_start
async def on_chat_start():

    user_env = cl.user_session.get("env")
    os.environ["GROQ_API_KEY"] = user_env.get("GROQ_API_KEY")

    settings = await cl.ChatSettings(
        [
            Select(
                id="Model",
                label="Open Source Model",
                values=["llama3-8b-8192", "llama3-70b-8192", "mixtral-8x7b-32768", "gemma-7b-it"],
                initial_index=0,
            )
        ]
    ).send()

    files = None #Initialize variable to store uploaded files

    # Wait for the user to upload a 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] # Get the first uploaded file
    
    # Inform the user that processing has started
    msg = cl.Message(content=f"Processing `{file.name}`...")
    await msg.send()

    # Read the PDF file
    pdf = PyPDF2.PdfReader(file.path)
    pdf_text = ""
    for page in pdf.pages:
        pdf_text += page.extract_text()
        

    # Split the text into chunks
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    texts = text_splitter.split_text(pdf_text)

    # Create a metadata for each chunk
    metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]

    # Create a Chroma vector store
    embeddings = OllamaEmbeddings(model="nomic-embed-text")
    #embeddings = OllamaEmbeddings(model="llama2:7b")
    docsearch = await cl.make_async(Chroma.from_texts)(
        texts, embeddings, metadatas=metadatas, persist_directory='./chroma_db'
    )
    docsearch.persist()
    

    # Let the user know that the system is ready
    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
    await msg.update()

    await setup_agent(settings)
    

@cl.on_settings_update
async def setup_agent(settings):
    print("Setup agent with settings:", settings)

    user_env = cl.user_session.get("env")
    os.environ["GROQ_API_KEY"] = user_env.get("GROQ_API_KEY")

    embeddings = OllamaEmbeddings(model="nomic-embed-text")
    memory=get_memory()
    
    docsearch = await cl.make_async(Chroma)(
        persist_directory="./chroma_db",
        embedding_function=embeddings
    )

    # Create a chain that uses the Chroma vector store
    chain = ConversationalRetrievalChain.from_llm(
        llm = ChatGroq(model=settings["Model"]),
        chain_type="stuff",
        retriever=docsearch.as_retriever(),
        memory=memory,
        return_source_documents=True,
    )

    #store the chain in user session
    cl.user_session.set("chain", chain)


@cl.on_message
async def main(message: cl.Message):
        
     # Retrieve the chain from user session
    chain = cl.user_session.get("chain") 
    #call backs happens asynchronously/parallel 
    cb = cl.AsyncLangchainCallbackHandler()

    user_env = cl.user_session.get("env")
    os.environ["GROQ_API_KEY"] = user_env.get("GROQ_API_KEY")


    print(chain)
    
    # call the chain with user's message content
    res = await chain.ainvoke(message.content, callbacks=[cb])
    answer = res["answer"]
    source_documents = res["source_documents"] 

    text_elements = [] # Initialize list to store text elements
    
    # Process source documents if available
    if source_documents:
        for source_idx, source_doc in enumerate(source_documents):
            source_name = f"source_{source_idx}"
            # Create the text element referenced in the message
            text_elements.append(
                cl.Text(content=source_doc.page_content, name=source_name)
            )
        source_names = [text_el.name for text_el in text_elements]
        
         # Add source references to the answer
        if source_names:
            answer += f"\nSources: {', '.join(source_names)}"
        else:
            answer += "\nNo sources found"
    #return results
    await cl.Message(content=answer, elements=text_elements).send()