app.py

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

def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_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_vectorstore(text_chunks, openai_api_key, model):
    embeddings = OpenAIEmbeddings(api_key=openai_api_key, model=model)
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

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

def handle_userinput(user_question):
    response = st.session_state.conversation({'question': user_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():
    st.set_page_config(page_title="Chat with multiple PDFs",
                       page_icon=":books:")
    st.write(css, unsafe_allow_html=True)

    openai_api_key = st.sidebar.text_input("Enter your OpenAI API Key", type="password")

    # Pilihan model
    model_options = [
        "text-embedding-3-large",
        "text-embedding-3-small",
        "text-embedding-ada-002"
    ]
    selected_model = st.sidebar.selectbox("Select the model", model_options)

    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 multiple PDFs :books:")
    st.write("Please enter the data in the menu on the left")  # Menambahkan teks di sini
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader(
            "Upload your PDFs here", accept_multiple_files=True)
        
        if pdf_docs and openai_api_key:
            with st.spinner("Processing"):
                # get pdf text
                raw_text = get_pdf_text(pdf_docs)

                # get the text chunks
                text_chunks = get_text_chunks(raw_text)

                # create vector store
                vectorstore = get_vectorstore(text_chunks, openai_api_key, selected_model)

                # create conversation chain
                st.session_state.conversation = get_conversation_chain(
                    vectorstore, openai_api_key)

if __name__ == '__main__':
    main()