app.py

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("HuggingfaceH4/zephyr-7b-beta")


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})

    # ストリーミングを無効にして、単一の応答を取得
    response = client.chat_completion(
        messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
    )

    return response.choices[0].message.content

"""
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="ユーザーの質問や依頼にのみ答えてください。ポジティブに答えてください。", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="新規トークン最大"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="温度"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (核 sampling)",
        ),
    ],
    examples=[
            ["日本で有名なものと言えば"],
            ["レポートを書いてくれる？"],
            ["C#で素数を判定するコードを書いて"],
            ["250の約数は？"],
        ],
    concurrency_limit=30  # 例: 同時に4つのリクエストを処理
)


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