app.py

from flask import Flask, render_template, request, jsonify
from huggingface_hub import InferenceClient
import gradio as gr

app = Flask(__name__)

client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")

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 generate(
    prompt, history, system_prompt, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
):
    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(f"{system_prompt}, {prompt}", history)
    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output

@app.route('/generate', methods=['POST'])
def generate_response():
    data = request.get_json()
    prompt = data['prompt']
    history = data['history']
    system_prompt = data['system_prompt']
    temperature = data['temperature']
    max_new_tokens = data['max_new_tokens']
    top_p = data['top_p']
    repetition_penalty = data['repetition_penalty']

    result = list(generate(prompt, history, system_prompt, temperature, max_new_tokens, top_p, repetition_penalty))

    return jsonify({'result': result})

if __name__ == '__main__':
    app.run(port=7860)