app.py

from typing import Iterator

import gradio as gr
import torch

from model import get_input_token_length, run

DEFAULT_SYSTEM_PROMPT = """\
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\
"""
MAX_MAX_NEW_TOKENS = 2048
DEFAULT_MAX_NEW_TOKENS = 1024
MAX_INPUT_TOKEN_LENGTH = 4000

DESCRIPTION = """
# CareLlama-关怀羊驼

- CareLlama (关怀羊驼)是一个医疗大语言模型，同时它集合了数十个公开可用的医疗微调数据集和开放可用的医疗大语言模型以促进医疗LLM快速发展。
- Medical LLM, Open Source Driven for a Healthy Future.

"""

LICENSE = """
<p/>

---
本项目相关资源仅供学术研究之用，严禁用于商业用途。使用涉及第三方代码的部分时，请严格遵循相应的开源协议。模型生成的内容受模型计算、随机性和量化精度损失等因素影响，本项目无法对其准确性作出保证。即使本项目模型输出符合医学事实，也不能被用作实际医学诊断的依据。对于模型输出的任何内容，本项目不承担任何法律责任，亦不对因使用相关资源和输出结果而可能产生的任何损失承担责任。
"""

if not torch.cuda.is_available():
    DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'


def clear_and_save_textbox(message: str) -> tuple[str, str]:
    return '', message


def display_input(message: str,
                  history: list[tuple[str, str]]) -> list[tuple[str, str]]:
    history.append((message, ''))
    return history


def delete_prev_fn(
        history: list[tuple[str, str]]) -> tuple[list[tuple[str, str]], str]:
    try:
        message, _ = history.pop()
    except IndexError:
        message = ''
    return history, message or ''


def generate(
    message: str,
    history_with_input: list[tuple[str, str]],
    system_prompt: str,
    max_new_tokens: int,
    temperature: float,
    top_p: float,
    top_k: int,
) -> Iterator[list[tuple[str, str]]]:
    if max_new_tokens > MAX_MAX_NEW_TOKENS:
        raise ValueError

    history = history_with_input[:-1]
    generator = run(message, history, system_prompt, max_new_tokens, temperature, top_p, top_k)
    try:
        first_response = next(generator)
        yield history + [(message, first_response)]
    except StopIteration:
        yield history + [(message, '')]
    for response in generator:
        yield history + [(message, response)]


def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
    generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 1, 0.95, 50)
    for x in generator:
        pass
    return '', x


def check_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> None:
    input_token_length = get_input_token_length(message, chat_history, system_prompt)
    if input_token_length > MAX_INPUT_TOKEN_LENGTH:
        raise gr.Error(f'The accumulated input is too long ({input_token_length} > {MAX_INPUT_TOKEN_LENGTH}). Clear your chat history and try again.')


with gr.Blocks(css='style.css') as demo:
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(value='Duplicate Space for private use',
                       elem_id='duplicate-button')

    with gr.Group():
        chatbot = gr.Chatbot(label='CareLlama')
        with gr.Row():
            textbox = gr.Textbox(
                container=False,
                show_label=False,
                placeholder='请输入内容...',
                scale=10,
            )
            submit_button = gr.Button('Submit',
                                      variant='primary',
                                      scale=1,
                                      min_width=0)
    with gr.Row():
        retry_button = gr.Button('🔄  重试', variant='secondary')
        undo_button = gr.Button('↩️ 撤销', variant='secondary')
        clear_button = gr.Button('🗑️  清除', variant='secondary')

    saved_input = gr.State()

    with gr.Accordion(label='Advanced options', open=False):
        system_prompt = gr.Textbox(label='System prompt',
                                   value=DEFAULT_SYSTEM_PROMPT,
                                   lines=6)
        max_new_tokens = gr.Slider(
            label='Max new tokens',
            minimum=1,
            maximum=MAX_MAX_NEW_TOKENS,
            step=1,
            value=DEFAULT_MAX_NEW_TOKENS,
        )
        temperature = gr.Slider(
            label='Temperature',
            minimum=0.1,
            maximum=4.0,
            step=0.1,
            value=1.0,
        )
        top_p = gr.Slider(
            label='Top-p (nucleus sampling)',
            minimum=0.05,
            maximum=1.0,
            step=0.05,
            value=0.95,
        )
        top_k = gr.Slider(
            label='Top-k',
            minimum=1,
            maximum=1000,
            step=1,
            value=50,
        )

    gr.Examples(
        examples=[
            '你好'
        ],
        inputs=textbox,
        outputs=[textbox, chatbot],
        fn=process_example,
        cache_examples=True,
    )

    gr.Markdown(LICENSE)

    textbox.submit(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=check_input_token_length,
        inputs=[saved_input, chatbot, system_prompt],
        api_name=False,
        queue=False,
    ).success(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    button_event_preprocess = submit_button.click(
        fn=clear_and_save_textbox,
        inputs=textbox,
        outputs=[textbox, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=check_input_token_length,
        inputs=[saved_input, chatbot, system_prompt],
        api_name=False,
        queue=False,
    ).success(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    retry_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=display_input,
        inputs=[saved_input, chatbot],
        outputs=chatbot,
        api_name=False,
        queue=False,
    ).then(
        fn=generate,
        inputs=[
            saved_input,
            chatbot,
            system_prompt,
            max_new_tokens,
            temperature,
            top_p,
            top_k,
        ],
        outputs=chatbot,
        api_name=False,
    )

    undo_button.click(
        fn=delete_prev_fn,
        inputs=chatbot,
        outputs=[chatbot, saved_input],
        api_name=False,
        queue=False,
    ).then(
        fn=lambda x: x,
        inputs=[saved_input],
        outputs=textbox,
        api_name=False,
        queue=False,
    )

    clear_button.click(
        fn=lambda: ([], ''),
        outputs=[chatbot, saved_input],
        queue=False,
        api_name=False,
    )

demo.queue(max_size=20).launch()