from langchain_huggingface import HuggingFaceEndpoint
import streamlit as st
model_id="mistralai/Mistral-7B-Instruct-v0.3"
def get_llm_hf_inference(model_id=model_id, max_new_tokens=128, temperature=0.1):
    llm = HuggingFaceEndpoint(
        repo_id=model_id,
        max_new_tokens=max_new_tokens,
        temperature=temperature,
        token = os.getenv("HF_TOKEN")
    )
    return llm