import streamlit as st 
from langchain.document_loaders import TextLoader
import os
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Chroma
from langchain import HuggingFaceHub
from langchain.chains import RetrievalQA


# load huggingface api key
hub_token = os.environ["hub_key"]

# Load text
loader = TextLoader("testing.txt")
documents = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=20)
docs = splitter.split_documents(documents)

embeddings = HuggingFaceEmbeddings()
doc_search = Chroma.from_documents(docs, embeddings)

repo_id = "mistralai/Mistral-7B-v0.1"
llm = HuggingFaceHub(repo_id=repo_id, huggingfacehub_api_token=hub_token, model_kwargs={'temperature': 0.2,'min_length': 4000})

from langchain.schema import retriever
retireval_chain = RetrievalQA.from_chain_type(llm, chain_type="stuff", retriever=doc_search.as_retriever())

if query := st.chat_input("Enter your query "):
    with st.chat_message("Assistant"):
        st.write(retireval_chain.run(query))