| import gradio as gr |
| from huggingface_hub import InferenceClient |
|
|
|
|
| def respond( |
| message, |
| history: list[dict[str, str]], |
| system_message, |
| max_tokens, |
| temperature, |
| top_p, |
| hf_token: gr.OAuthToken, |
| ): |
| """ |
| 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 |
| """ |
| if hf_token is None: |
| yield "⚠️ Silakan login dulu dengan tombol Login di sidebar." |
| return |
|
|
| client = InferenceClient(token=hf_token.token) |
|
|
| messages = [{"role": "system", "content": system_message}] |
| messages.extend(history) |
| messages.append({"role": "user", "content": message}) |
|
|
| response = "" |
|
|
| try: |
| for chunk in client.chat_completion( |
| messages, |
| model="openai/gpt-oss-20b", |
| max_tokens=max_tokens, |
| stream=True, |
| temperature=temperature, |
| top_p=top_p, |
| ): |
| choices = chunk.choices |
| if len(choices) and choices[0].delta.content: |
| response += choices[0].delta.content |
| yield response |
| except Exception as e: |
| yield f"❌ Error: {e}" |
|
|
|
|
| """ |
| For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface |
| """ |
| chatbot = gr.ChatInterface( |
| respond, |
| 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)", |
| ), |
| ], |
| ) |
|
|
| with gr.Blocks() as demo: |
| with gr.Sidebar(): |
| gr.LoginButton() |
| chatbot.render() |
|
|
|
|
| if __name__ == "__main__": |
| demo.launch() |
|
|
