Update app.py

app.py

@@ -11,13 +11,14 @@ client = InferenceClient(token=HF_TOKEN)
 
 # Chat function
 def respond(message, history, max_tokens, temperature, top_p):
-    # Build prompt in OpenAI-style
+    # Build prompt
     prompt = [{"role": "system", "content": system_message}]
-    for msg in history:
-        if msg["role"] == "user":
-            prompt.append({"role": "user", "content": msg["content"]})
-        elif msg["role"] == "assistant":
-            prompt.append({"role": "assistant", "content": msg["content"]})
+
+    # history is a list of (user, assistant) tuples
+    for user_msg, assistant_msg in history:
+        prompt.append({"role": "user", "content": user_msg})
+        prompt.append({"role": "assistant", "content": assistant_msg})
+
     prompt.append({"role": "user", "content": message})
 
     response = []
@@ -32,7 +33,7 @@ def respond(message, history, max_tokens, temperature, top_p):
 
     for chunk in stream:
         if not chunk.choices:
-            continue  # skip empty chunks safely
+            continue
         delta = chunk.choices[0].delta
         token = getattr(delta, "content", None)
         if token:
@@ -42,7 +43,6 @@ def respond(message, history, max_tokens, temperature, top_p):
 # UI
 app = gr.ChatInterface(
     fn=respond,
-    type="messages",  # ✅ fixes Gradio warning
     additional_inputs=[
         gr.Slider(16, 2048, value=512, step=1, label="Max Tokens"),
         gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature"),