middlewares/chat_client.py

from huggingface_hub import InferenceClient
import os
from dotenv import load_dotenv

load_dotenv()

API_TOKEN = os.getenv("HF_TOKEN")


def format_prompt(message, history):
    prompt = "<s>"
    for user_prompt, bot_response in history:
        prompt += f"[INST] {user_prompt} [/INST]"
        prompt += f" {bot_response}</s> "
    prompt += f"[INST] {message} [/INST]"
    return prompt


def chat(
    prompt,
    history,
    chat_client="mistralai/Mistral-7B-Instruct-v0.1",
    temperature=0.9,
    max_new_tokens=256,
    top_p=0.95,
    repetition_penalty=1.0,
):
    client = InferenceClient(chat_client, token=API_TOKEN)
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(prompt, history)

    stream = client.text_generation(
        formatted_prompt,
        **generate_kwargs,
        stream=True,
        details=True,
        return_full_text=False,
    )

    return stream