Update app.py

app.py

@@ -1,53 +1,65 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# HuggingFace API Client
-client = InferenceClient(model="Futuresony/future_ai_12_10_2024.gguf")
+"""
+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("Futuresony/future_ai_12_10_2024.gguf")
 
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    """
-    Function to process user messages and return AI responses.
-    """
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     messages = [{"role": "system", "content": system_message}]
-    
-    # Append conversation history
-    for user, assistant in history:
-        if user:
-            messages.append({"role": "user", "content": user})
-        if assistant:
-            messages.append({"role": "assistant", "content": assistant})
-    
-    # Add user 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})
 
     response = ""
-    try:
-        # Stream AI-generated responses
-        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
-            response += token
-            yield response
-    except Exception as e:
-        yield f"Error: {str(e)}"
-
-# Gradio Chat Interface
+
+    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
+
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
 demo = gr.ChatInterface(
-    fn=respond,
-    inputs=[
-        gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
-        gr.Slider(1, 2048, value=512, step=1, label="Max Tokens"),
-        gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-P"),
+    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)",
+        ),
     ],
 )
 
-# Run Gradio App
+
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch()