app.py

import os
import json
import gradio as gr
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1",token=os.getenv('HUGGINGFACE_TOKEN').strip())

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_response(
    prompt,
    history: list[tuple[str, str]],
    system_prompt: list[tuple[str,str]],
    max_tokens,
    temperature,
    top_p,
):
    print('=====================')
    print(type(history))
    print(history)
    print(type(system_prompt))
    print('=====================')
    listObject = ""
    try:
        listObject = json.loads(system_prompt)
    except ValueError:
        print("system_prompt not a list")

    if isinstance(listObject,list):
        history = listObject
        print("system_prompt as history")
    else:
        print(type(system_prompt))
        print(system_prompt)
    print('=====================')

    #system_prompt = "i'm a friendly robot"   
    sys_message = ""
    print('=====================')
    print(prompt)
    print(history)
    print(system_prompt)
    print(max_tokens)
    print(temperature)
    print(top_p)
    print('=====================')
    formatted_prompt = format_prompt(f"{sys_message}, {prompt}", history)
    stream = client.text_generation(formatted_prompt,stream=True, max_new_tokens=256, return_full_text=False)
    output = ""
    for response in stream:
        output += response
        yield response
    #return output


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    print("============= make chat_completion  =============")
    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    #respond,
    generate_response,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch(share=True)