app.py

import streamlit as st
import tempfile
import pandas as pd 
from langchain import HuggingFacePipeline 
from transformers import AutoTokenizer 
from langchain.embeddings import HuggingFaceEmbeddings 
from langchain.document_loaders.csv_loader import CSVLoader 
from langchain.vectorstores import FAISS 
from langchain.chains import RetrievalQA 
import transformers 
import torch 
import textwrap 

def main():
    st.set_page_config(page_title="👨‍💻 Talk with BORROWER data")
    st.title("👨‍💻 Talk with BORROWER data")
    uploaded_file = st.sidebar.file_uploader("Upload your Data", type="csv")

    query = st.text_input("Send a Message")
    if st.button("Submit Query", type="primary"):
        DB_FAISS_PATH = "vectorstore/db_faiss"

        if uploaded_file :
        #use tempfile because CSVLoader only accepts a file_path
            with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
                tmp_file.write(uploaded_file.getvalue())
                tmp_file_path = tmp_file.name

            loader = CSVLoader(file_path=tmp_file_path, encoding="utf-8", csv_args={
                        'delimiter': ','})
            data = loader.load()
            st.write(data)

            model = "daryl149/llama-2-7b-chat-hf" 
            tokenizer = AutoTokenizer.from_pretrained(model) 
            pipeline = transformers.pipeline("text-generation", #task 
                                              model=model, 
                                              tokenizer=tokenizer, 
                                              torch_dtype=torch.bfloat16, 
                                              trust_remote_code=True, 
                                              device_map="auto", 
                                              max_length=1000, 
                                              do_sample=True, 
                                              top_k=10, 
                                              num_return_sequences=1, 
                                              eos_token_id=tokenizer.eos_token_id 
            ) 

            llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0}) 
            embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2') 
            vectorstore = FAISS.from_documents(data, embeddings)

            vectorstore.save_local(DB_FAISS_PATH)

            chain =  RetrievalQA.from_chain_type(llm=llm, chain_type = "stuff",return_source_documents=True, retriever=vectorstore.as_retriever()) 
            result=chain(query)
            wrapped_text = textwrap.fill(result['result'], width=500) 

            st.write(wrapped_text)

if __name__ == '__main__':
    main()