update respond func

app.py

@@ -9,37 +9,17 @@ For more information on `huggingface_hub` Inference API support, please check th
 client = InferenceClient("EleutherAI/gpt-neo-125M")
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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]})
-
-    messages.append({"role": "user", "content": message})
-
-    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
-
-        response += token
-        yield response
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Construct the prompt with system message, history, and user input
+    prompt = system_message + "\n" + "\n".join([f"User: {msg[0]}\nAssistant: {msg[1]}" for msg in history if msg[0] and msg[1]])
+    prompt += f"\nUser: {message}\nAssistant:"
+
+    # Generate a response using the model
+    response = client(prompt, max_length=max_tokens, temperature=temperature, top_p=top_p, do_sample=True)[0]['generated_text']
+    
+    # Extract the assistant's response part (after "Assistant:")
+    assistant_response = response.split("Assistant:", 1)[-1].strip()
+    return assistant_response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface