Update app.py

app.py

@@ -1,64 +1,82 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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")
-
+# Define available models (update with your actual model IDs)
+model_list = {
+    "Safe LM": "HuggingFaceH4/zephyr-7b-beta",  # Replace with your Safe LM model ID
+    "Zephyr Beta": "HuggingFaceH4/zephyr-7b-beta",
+    "Another Model": "HuggingFaceH4/zephyr-7b-beta"
+}
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p, selected_model):
+    # Look up the model ID from our list based on the dropdown selection
+    model_id = model_list.get(selected_model, "HuggingFaceH4/zephyr-7b-beta")
+    # Create an InferenceClient for the selected model
+    client = InferenceClient(model_id)
+    
+    # Build the conversation history into the message list
     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]})
-
+    for user_msg, assistant_msg in history or []:
+        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 = ""
-
-    for message in client.chat_completion(
+    # Stream the response from the client
+    for token_message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
+        token = token_message.choices[0].delta.content
         response += token
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# CSS styling: pastel backgrounds, gentle light colors, and rounded corners for a safe vibe
+css = """
+body { background-color: #FAF3E0; }
+.gradio-container { background-color: #FFFFFF; border-radius: 16px; padding: 20px; }
+button, input, .gradio-dropdown, .gradio-slider, textarea { border-radius: 16px; }
+.gradio-chat { border-radius: 16px; }
 """
-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(css=css) as demo:
+    with gr.Row():
+        # Left sidebar: Model selector
+        with gr.Column(scale=1):
+            gr.Markdown("## Models")
+            model_dropdown = gr.Dropdown(
+                choices=list(model_list.keys()),
+                label="Select Model",
+                value="Safe LM"
+            )
+        # Main area: Chat interface and settings
+        with gr.Column(scale=3):
+            gr.Markdown("## Chat Interface")
+            chatbot = gr.Chatbot(label="Chat with your Model")
+            user_input = gr.Textbox(placeholder="Enter your message...", label="Your Message")
+            with gr.Row():
+                send_button = gr.Button("Send")
+                clear_button = gr.Button("Clear Chat")
+            gr.Markdown("### Chat Settings")
+            system_message = gr.Textbox(value="You are a friendly Chatbot.", label="System Message")
+            max_tokens_slider = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max New Tokens")
+            temperature_slider = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
+            top_p_slider = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
+    
+    # When "Send" is clicked, run the respond() function and update the chat interface.
+    send_button.click(
+        fn=respond,
+        inputs=[user_input, chatbot, system_message, max_tokens_slider, temperature_slider, top_p_slider, model_dropdown],
+        outputs=[user_input, chatbot],
+    )
+    
+    # Clear the chat history when "Clear Chat" is clicked.
+    clear_button.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
     demo.launch()