app.py

from huggingface_hub import InferenceClient
import gradio as gr
import random
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
     
from prompts import GAME_MASTER, COMPRESS_HISTORY
def format_prompt(message, history):
    prompt=""
    '''
    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 compress_history(purpose, task, history):
    resp = run_gpt(
        COMPRESS_HISTORY,
        stop_tokens=["observation:", "task:", "action:", "thought:"],
        max_tokens=512,
        seed=random.randint(1,1000000000),
        purpose=purpose,
        task=task,
        history=history,
    )
    history = resp
    return history
MAX_HISTORY=100

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=random.randint(1,99999999999)
        #seed=42,
    )
    cnt=0
    for ea in history:
        print (ea)
        for l in ea:
            print (l)
            cnt+=len(l.split("\n"))
    print(f'cnt:: {cnt}')
    if cnt > MAX_HISTORY:
        history = compress_history(history, prompt, history)
    formatted_prompt = format_prompt(f"{GAME_MASTER}, {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


additional_inputs=[
    gr.Textbox(
        label="System Prompt",
        max_lines=1,
        interactive=True,
    ),
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=1048,
        minimum=0,
        maximum=1048*10,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

examples=[["Start the Game", None, None, None, None, None, ],
          ["Start a Game based in the year 1322", None, None, None, None, None,],
         ]

gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="Mixtral RPG Game Master",
    examples=examples,
    concurrency_limit=20,
).launch(share=True,show_api=True)