app.py

import os
import gradio as gr
from huggingface_hub import InferenceClient

# 1. Define the list of available models
# You can add any model ID from Hugging Face that supports the Inference API
MODELS = [
    "baidu/ERNIE-4.5-21B-A3B-PT",
    "moonshotai/Kimi-K2-Thinking",
    "meta-llama/Meta-Llama-3-8B-Instruct",
    "openai/gpt-oss-20b",
    "openai/gpt-oss-120b",
]

def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    model_id, # 2. Accept model_id as an argument
):
    # Load the token from the environment variable "HF_TOKEN"
    token = os.getenv("HF_TOKEN")
    
    # Check if token exists (Optional safety check)
    if not token:
        yield "Error: HF_TOKEN environment variable is not set. Please set it in your terminal."
        return

    # 3. Initialize the client with the USER-SELECTED model
    client = InferenceClient(token=token, model=model_id)

    messages = [{"role": "system", "content": system_message}]

    # History format: [{"role": "user", "content": "..."}, {"role": "assistant", "content": "..."}]
    messages.extend(history)
    messages.append({"role": "user", "content": message})

    response = ""

    try:
        for message in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            choices = message.choices
            token = ""
            if len(choices) and choices[0].delta.content:
                token = choices[0].delta.content

            response += token
            yield response
    except Exception as e:
        yield f"API Error for model {model_id}: {str(e)}"

"""
ChatInterface Configuration
"""
chatbot = gr.ChatInterface(
    respond,
    type="messages",
    fill_height=True,
    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)",
        ),
        # 4. Add the Dropdown for Model Selection
        gr.Dropdown(
            choices=MODELS, 
            value=MODELS[0], # Default model
            label="Select Model", 
            interactive=True
        ),
    ],
)

# Clean Layout without Sidebar/Login
with gr.Blocks(fill_height=True) as demo:
    chatbot.render()

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