app.py

import streamlit as st
from dotenv import load_dotenv
from langchain.text_splitter import RecursiveCharacterTextSplitter
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 langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
import tempfile
import os

css = """
    <style>
    /* 여기에 CSS 코드를 넣어주세요 */
    </style>
"""

def get_pdf_text(pdf_docs):
    temp_dir = tempfile.TemporaryDirectory()
    temp_filepath = os.path.join(temp_dir.name, pdf_docs.name)
    with open(temp_filepath, "wb") as f:
        f.write(pdf_docs.getvalue())
    pdf_loader = PyPDFLoader(temp_filepath)
    pdf_doc = pdf_loader.load()
    return pdf_doc

def get_text_file(docs):
    text_loader = TextLoader(docs.name)
    text = text_loader.load()
    return [text]

def get_csv_file(docs):
    csv_loader = CSVLoader(docs.name)
    csv_text = csv_loader.load()
    return csv_text.values.tolist()

def get_json_file(docs):
    json_loader = JSONLoader(docs.name)
    json_text = json_loader.load()
    return [json_text]

def get_text_chunks(documents):
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )

    documents = text_splitter.split_documents(documents)
    return documents

def get_vectorstore(text_chunks):
    embeddings = OpenAIEmbeddings()
    vectorstore = FAISS.from_documents(text_chunks, embeddings)
    return vectorstore

def get_conversation_chain(vectorstore):
    gpt_model_name = 'gpt-3.5-turbo'
    llm = ChatOpenAI(model_name=gpt_model_name)

    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():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple Files",
                       page_icon=":books:")
    st.write(css, 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 multiple Files :")
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        openai_key = st.text_input("Paste your OpenAI API key (sk-...)")
        if openai_key:
            os.environ["OPENAI_API_KEY"] = openai_key

        st.subheader("Your documents")
        docs = st.file_uploader(
            "Upload your files here and click on 'Process'", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                doc_list = []

                for file in docs:
                    if file.type == 'text/plain':
                        doc_list.extend(get_text_file(file))
                    elif file.type in ['application/octet-stream', 'application/pdf']:
                        doc_list.extend(get_pdf_text(file))
                    elif file.type == 'text/csv':
                        doc_list.extend(get_csv_file(file))
                    elif file.type == 'application/json':
                        doc_list.extend(get_json_file(file))

                text_chunks = get_text_chunks(doc_list)
                vectorstore = get_vectorstore(text_chunks)
                st.session_state.conversation = get_conversation_chain(
                    vectorstore)

if __name__ == '__main__':
    main()