Update app.py

app.py

@@ -1,64 +1,110 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from huggingface_hub import InferenceClient, InferenceTimeoutError
+import logging
 
-"""
-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")
+# Set up logging
+logging.basicConfig(level=logging.INFO)
 
+# Initialize client with timeout
+client = InferenceClient("hackergeek/gemma-finetuned", timeout=30)
 
 def respond(
-    message,
+    message: str,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
-    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]})
+    """
+    Handles chat responses with error handling and validation
+    """
+    try:
+        # Validate system message
+        if not system_message.strip():
+            system_message = "You are a helpful AI assistant."
 
-    messages.append({"role": "user", "content": message})
+        # Build message history
+        messages = [{"role": "system", "content": system_message}]
+        
+        for user_msg, assistant_msg in history:
+            if user_msg:
+                messages.append({"role": "user", "content": user_msg})
+            if assistant_msg:
+                messages.append({"role": "assistant", "content": assistant_msg})
+        
+        messages.append({"role": "user", "content": message})
 
-    response = ""
+        response = ""
+        
+        # Stream the response
+        for chunk in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            if chunk.choices and chunk.choices[0].delta.content:
+                token = chunk.choices[0].delta.content
+                response += token
+                yield 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
+    except InferenceTimeoutError:
+        logging.error("API request timed out")
+        yield "Error: Request timed out. Please try again."
+    except Exception as e:
+        logging.error(f"API error: {str(e)}")
+        yield f"Error: {str(e)}. Please check your input and try again."
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# Custom CSS for better appearance
+custom_css = """
+#chatbot { min-height: 400px; }
+.dark #chatbot { font-size: 14px !important; }
+footer { visibility: hidden; }
 """
-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)",
-        ),
-    ],
-)
 
+# Configure interface
+with gr.Blocks(css=custom_css, title="Gemma Chatbot") as demo:
+    gr.Markdown("# 🚀 Gemma Fine-Tuned Chatbot")
+    gr.Markdown("Chat with the fine-tuned Gemma AI assistant!")
+    
+    with gr.Accordion("⚙️ Advanced Settings", open=False):
+        system_input = gr.Textbox(
+            value="You are a helpful AI assistant.",
+            label="System Role",
+            info="Initial instructions for the AI"
+        )
+        max_tokens = gr.Slider(
+            minimum=32, maximum=2048, value=512,
+            step=32, label="Max Response Length"
+        )
+        temperature = gr.Slider(
+            minimum=0.1, maximum=2.0, value=0.7,
+            step=0.1, label="Creativity (Temperature)"
+        )
+        top_p = gr.Slider(
+            minimum=0.1, maximum=1.0, value=0.95,
+            step=0.05, label="Focus (Top-p)"
+        )
+    
+    chat_interface = gr.ChatInterface(
+        respond,
+        additional_inputs=[
+            system_input,
+            max_tokens,
+            temperature,
+            top_p
+        ],
+        examples=[
+            ["Explain quantum computing in simple terms"],
+            ["What's the weather like in Paris?"],
+            ["Write a poem about artificial intelligence"]
+        ],
+        retry_btn=None,
+        undo_btn=None,
+        clear_btn="✨ New Chat",
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(server_name="0.0.0.0", server_port=7860)