Update app.py

app.py

@@ -1,88 +1,128 @@
 import gradio as gr
 from huggingface_hub import InferenceClient, login
+import os
+from typing import List, Tuple, Optional
 
+# Available models for selection
+AVAILABLE_MODELS = [
+    "Qwen/Qwen3-Coder-480B-A35B-Instruct",
+    "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "meta-llama/Llama-3-70B-Instruct",
+]
 
-
+def initialize_client(token: str, model: str) -> Optional[InferenceClient]:
+    """Initialize the InferenceClient with the provided token and model."""
+    try:
+        login(token)
+        return InferenceClient(model=model)
+    except Exception as e:
+        return gr.Error(f"Failed to initialize client: {str(e)}")
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    model,
-    token,
-):
+    message: str,
+    history: List[Tuple[str, str]],
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
+    model: str,
+    token: str,
+) -> str:
     """
-    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
+    Generate a response using the Hugging Face Inference API.
+    Docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
-    
-    login(token)
-    client = InferenceClient(model)
-    messages = [
-        {
-            "role": "system", 
-            "content": system_message,
-        }
-    ]
+    if not token:
+        raise gr.Error("Please provide a valid Hugging Face API token.")
+    if not message.strip():
+        raise gr.Error("Input message cannot be empty.")
 
-    for val in history:
-        if val[0]:
-            messages.append(
-                {"role": "user",
-                 "content": val[0],
-                },
-            )
-        if val[1]:
-            messages.append(
-                {"role": "assistant",
-                 "content": val[1],
-                }
-            )
+    client = initialize_client(token, model)
+    if isinstance(client, gr.Error):
+        raise client
 
-    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})
 
+    # Generate response
     response = ""
+    try:
+        for chunk in client.chat_completion(
+            messages=messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = chunk.choices[0].delta.content or ""
+            response += token
+            yield response
+    except Exception as e:
+        raise gr.Error(f"Error during inference: {str(e)}")
 
-    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
-
+# Load token from environment variable for security
+HF_TOKEN = os.getenv("HF_TOKEN", "")
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Create Gradio interface
 demo = gr.ChatInterface(
-    respond,
+    fn=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.Textbox(
+            value="You are a friendly and helpful Chatbot.",
+            label="System Message",
+            placeholder="Enter the system prompt here...",
+        ),
+        gr.Slider(
+            minimum=1,
+            maximum=2048,
+            value=512,
+            step=1,
+            label="Max New Tokens",
+            info="Controls the maximum length of the generated response.",
+        ),
+        gr.Slider(
+            minimum=0.1,
+            maximum=4.0,
+            value=0.7,
+            step=0.1,
+            label="Temperature",
+            info="Controls randomness (higher = more creative, lower = more deterministic).",
+        ),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
             value=0.95,
             step=0.05,
-            label="Top-p (nucleus sampling)",
+            label="Top-p (Nucleus Sampling)",
+            info="Controls diversity via nucleus sampling.",
+        ),
+        gr.Dropdown(
+            choices=AVAILABLE_MODELS,
+            value=AVAILABLE_MODELS[0],
+            label="Model Selection",
+            info="Select the model to use for inference.",
+        ),
+        gr.Textbox(
+            value=HF_TOKEN,
+            label="Hugging Face API Token",
+            type="password",
+            placeholder="Enter your HF API token (or set HF_TOKEN env variable)",
         ),
-        gr.Textbox(value="Qwen/Qwen3-Coder-480B-A35B-Instruct", label="Qwen Models"),
-        gr.Textbox(value="HF...", label="System Api"),
     ],
+    title="Chatbot with Hugging Face Inference API",
+    description="Interact with a chatbot powered by Hugging Face models. Provide your API token and customize settings.",
+    theme="soft",
+    submit_btn="Send Message",
+    retry_btn="Retry",
+    undo_btn="Undo",
+    clear_btn="Clear Chat",
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()