Update app.py

app.py

@@ -1,88 +1,115 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from huggingface_hub import InferenceClient, HfApi
+from huggingface_hub.utils import HfHubHTTPError
+import os
 
-"""
-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 check_and_enable_api(model_id):
+    try:
+        api = HfApi()
+        model_info = api.model_info(model_id)
+        if not model_info.api:
+            api.toggle_model_api(model_id, True)
+            return "API was disabled. Now enabled for the model."
+        return "API already enabled for the model."
+    except Exception as e:
+        return f"Error checking 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_and_enable_api(model_id)
+        client = InferenceClient(model_id, token=token)
+        return f"✅ Connected to {model_id} | {status}"
+    except HfHubHTTPError as e:
+        return f"❌ API Error: {str(e)}"
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
+    message, 
+    history: list[tuple[str, str]], 
+    system_message, 
+    max_tokens, 
+    temperature, 
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    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)}"
 
-    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, history + [(message, response)]  # Return updated history
-
-
-"""
-Expose a standard API endpoint using gr.Interface alongside ChatInterface for interactive use.
-"""
-api_demo = gr.Interface(
-    fn=respond,
-    inputs=[
-        gr.Textbox(lines=2, label="Message"),
-        gr.State(),  # For chat history
-        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)",
-        ),
-    ],
-    outputs=[
-        gr.Textbox(label="Response"),  # Main response
-        gr.State()                     # Updated chat history
-    ],
-)
-
-# Combine both interfaces into a single app
-demo = 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:
+    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
+    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__":
-    # Launch both the ChatInterface for interactive use and API access
-    demo.launch(share=True, server_name="0.0.0.0", server_port=7860)
-    api_demo.launch(share=True, server_name="0.0.0.0", server_port=7861)
+    demo.launch()