Update app.py

app.py

@@ -1,64 +1,60 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from typing import List, Tuple
 
-"""
-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("Canstralian/RedTeamAI")
+# Initialize the Inference Client with the Canstralian/redteamai model
+client = InferenceClient("Canstralian/redteamai")
 
 
 def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    message: str,
+    history: List[Tuple[str, str]],
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
+    # Start with the system message in the conversation history
     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]})
-
+    
+    # Add the conversation history to the message
+    for user_message, assistant_reply in history:
+        if user_message:
+            messages.append({"role": "user", "content": user_message})
+        if assistant_reply:
+            messages.append({"role": "assistant", "content": assistant_reply})
+    
+    # Add the current user message
     messages.append({"role": "user", "content": message})
 
+    # Create the API request
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    for result in client.chat_completion(
+        messages=messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
+        stream=True  # Enable streaming for real-time responses
     ):
-        token = message.choices[0].delta.content
-
+        # Extract and accumulate the response as it streams
+        token = result['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(
-    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"),
+        yield response  # Yield response as it's generated
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="User Message", placeholder="Enter your message here..."),
+        gr.State(default=[], label="Chat History"),  # 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 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (Nucleus Sampling)"),
     ],
+    outputs=gr.Textbox(label="Assistant Response"),
+    live=True,  # Enable real-time updating of the response
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()