pdfchat/app.py at main · LakunleD/pdfchat · GitHub

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
import streamlit as st
from PyPDF2 import PdfReader
from dotenv import load_dotenv
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from htmlTemplates import css, bot_template, user_template

def get_pdf_text(pdf_files):
    text = ""
    for pdf_file in pdf_files:
        reader = PdfReader(pdf_file)
        for page in reader.pages:
            text += page.extract_text()
    return text

def get_text_chunks(text):
    text_splitter = CharacterTextSplitter(separator="\n", chunk_size =1000, chunk_overlap=200, length_function=len)
    chunks = text_splitter.split_text(text)
    return chunks

def get_vector_store(chunks):
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vector_store = FAISS.from_texts(chunks, embeddings)
    return vector_store

def get_conversation_chain(vectorstore):
    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=ChatOpenAI(),
        retriever=vectorstore.as_retriever(),
        memory=memory
    )
    return conversation_chain

def get_answer(conversation_chain, query):
    response = conversation_chain({"question": query})
    return response['answer']

def handle_userinput(question):
    response = st.session_state.conversation({"question": question})
    st.session_state.chat_history = response["chat_history"]

    for i, message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)

def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with PDF", page_icon=":books:")
    st.write(css, unsafe_allow_html=True)
    st.write(bot_template.replace("{{MSG}}", "hello Robot"), unsafe_allow_html=True)
    st.write(user_template.replace("{{MSG}}", "hello Human"), unsafe_allow_html=True)

    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header("Chat with PDF :books:")
    user_question = st.text_input("Ask a question about your PDF files:")
    if user_question:
        with st.spinner("Thinking..."):
            handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_files = st.file_uploader("Upload your PDF files", accept_multiple_files=True, type=["pdf"])
        if st.button("Process"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(pdf_files)
                text_chunks = get_text_chunks(raw_text)

                vectorstore = get_vector_store(text_chunks)

                st.session_state.conversation = get_conversation_chain(vectorstore)

    st.session_state.conversation


if __name__ == '__main__':
    main()