app.py

import gradio as gr
from huggingface_hub import InferenceClient, HfApi
from huggingface_hub.utils import HfHubHTTPError
import os

def check_api_status(model_id, token):
    try:
        client = InferenceClient(model_id, token=token)
        # Test if we can connect to the API
        response = client.chat_completion(
            [{"role": "user", "content": "test"}],
            max_tokens=1,
            stream=False
        )
        return "API is accessible and responding"
    except Exception as e:
        if "rate limit" in str(e).lower():
            return "API is accessible (rate limited)"
        return f"API status: {str(e)}"

def get_api_status():
    token = os.getenv('HF_TOKEN')
    model_id = "HuggingFaceH4/zephyr-7b-beta"
    
    if not token:
        return "⚠️ No API token found. Please set HF_TOKEN environment variable."
    
    try:
        status = check_api_status(model_id, token)
        return f"✅ Connected to {model_id} | {status}"
    except Exception as e:
        return f"❌ Error: {str(e)}"

def respond(
    message, 
    history: list[tuple[str, str]], 
    system_message, 
    max_tokens, 
    temperature, 
    top_p,
):
    token = os.getenv('HF_TOKEN')
    if not token:
        yield "Error: Please set your HuggingFace API token in the HF_TOKEN environment variable."
        return

    client = InferenceClient(
        "HuggingFaceH4/zephyr-7b-beta",
        token=token
    )
    
    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})
    
    try:
        response = ""
        for message in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            token = message.choices[0].delta.content
            response += token
            yield response
    except Exception as e:
        yield f"Error during chat completion: {str(e)}"

with gr.Blocks() as demo:
    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)",
            ),
        ],
    )
    
    # Add API status at the footer with improved status check
    footer = gr.HTML(
        value=f"<div style='text-align: center; padding: 10px; background-color: #f0f0f0; border-top: 1px solid #ddd;'>{get_api_status()}</div>",
        every=30  # Updates every 30 seconds
    )

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