app.py

import streamlit as st
# from dotenv import load_dotenv
import pickle
from PyPDF2 import PdfReader
from streamlit_extras.add_vertical_space import add_vertical_space
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.callbacks import get_openai_callback
import os
from langchain.vectorstores import Chroma
from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
from langchain.embeddings import HuggingFaceHubEmbeddings
# Sidebar contents
from langchain.llms import HuggingFaceHub
with st.sidebar:
    st.title('🤗💬 LLM Chat App')
    st.markdown('''
   ## About
   This app is an LLM-powered chatbot built using:
   - [Streamlit](https://streamlit.io/)
   - [LangChain](https://python.langchain.com/)
   - [OpenAI](https://platform.openai.com/docs/models) LLM model
 
   ''')
    add_vertical_space(5)
    st.write(
        'Made with ❤️ by [Prompt Engineer](https://youtube.com/@engineerprompt)')

# load_dotenv()

os.environ['OPEN_AI_APIKEY'] = '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'


def main():
    st.header("Chat with PDF 💬")

    # upload a PDF file
    pdf = st.file_uploader("Upload your PDF", type='pdf')

    # st.write(pdf)
    if pdf is not None:
        pdf_reader = PdfReader(pdf)

        text = ""
        for page in pdf_reader.pages:
            text += page.extract_text()

        text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=1000,
            chunk_overlap=200,
            length_function=len
        )
        chunks = text_splitter.split_text(text=text)

        # # embeddings
        store_name = pdf.name[:-4]
        st.write(f'{store_name}')
        # st.write(chunks)

        if os.path.exists(f"{store_name}.pkl"):
            with open(f"{store_name}.pkl", "rb") as f:
                VectorStore = pickle.load(f)
            # st.write('Embeddings Loaded from the Disk')s
        else:
            # embeddings = OpenAIEmbeddings(
            #     openai_api_key='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')
            # embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
            embeddings = HuggingFaceHubEmbeddings()
            VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
            # VectorStore=Chroma.from_documents(chunks, embeddings)
            with open(f"{store_name}.pkl", "wb") as f:
                pickle.dump(VectorStore, f)

        # embeddings = OpenAIEmbeddings()
        # VectorStore = FAISS.from_texts(chunks, embedding=embeddings)

        # Accept user questions/query
        query = st.text_input("Ask questions about your PDF file:")
        # st.write(query)

        if query:
            docs = VectorStore.similarity_search(query=query, k=3)
            llm = HuggingFaceHub(repo_id='OpenAssistant/oasst-sft-1-pythia-12b',
                                 token='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', model_kwargs={"temperature": 0.1, "max_new_tokens": 250})
            # llm = OpenAI()
            chain = load_qa_chain(llm=llm, chain_type="stuff")
            response = chain.run(input_documents=docs, question=query)
            # with get_openai_callback() as cb:
            #     response = chain.run(input_documents=docs, question=query)
            #     print(cb)
            st.write(response)


if __name__ == '__main__':
    main()