app.py

import openai
import gradio as gr
import os
os.system("sh run.sh")

client = openai.OpenAI(
    api_key="EMPTY",
    base_url="http://localhost:7777/v1"
)
def chatbot_mistral(messages:list,systemt_prompt=""):
    
    if messages[0]['role'] != "system":
        sys = {"role":"system","content":systemt_prompt}
        messages.insert(0,sys)
    else:
        messages[0]['content'] = systemt_prompt
        
    
    # model_name = "dewu-chat"
    call_args = {
        'temperature': 0.7,
        'top_p': 0.9,
        'top_k': 40,
        'max_tokens': 2048, # output-len
        'presence_penalty': 1.0,
        'frequency_penalty': 0.0,
        "repetition_penalty":1.0,
        "stop":["</s>"],
        # "stop":["<|eot_id|>","<|end_of_text|>"],
        "stream":True
    }
    
    # create a chat completion
    for chunk in openai.ChatCompletion.create(model="dewu-chat",messages=messages,extra_body=call_args):
        if hasattr(chunk.choices[0].delta, "content"):
            response = chunk.choices[0].delta.content
            yield response


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 = ""

    for i in chatbot_mistral(messages):
        yield i
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a helpful, respectful and honest assistant.Help humman as much as you can.", 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()