app_OG.py

from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.llms import HuggingFaceHub

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):
    # embeddings = OpenAIEmbeddings()
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore


def get_conversation_chain(vectorstore):
    # llm = ChatOpenAI()
    llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})

    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 main():

    # 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:")
    user_question = input("Ask a question about your documents:")
    if user_question:
        print(user_question)
    
    pdf_path = "data/2021-01-01-2021-01-31.pdf"
    pdf_docs = [pdf_path]

    raw_text = get_pdf_text(pdf_docs)
    text_chunks = get_text_chunks(raw_text)
    vectorstore = get_vectorstore(text_chunks)
    conversation = get_conversation_chain(
        vectorstore)
    print(conversation)


if __name__ == '__main__':
    main()