Update app.py

app.py

@@ -7,12 +7,15 @@ client = InferenceClient(MODEL_NAME)
 
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
+    if history is None:
+        history = []
+
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -29,23 +32,32 @@ def respond(
 
     try:
         response = client.fill_mask(message)
-        return {"prediction": response[0]["sequence"], "confidence": response[0]["score"]}
+        prediction = response[0]["sequence"]
+        confidence = response[0]["score"]
+
+        # Append to history
+        history.append((message, prediction))
+
+        return prediction, history  # Must return history explicitly as an output
     
     except Exception as e:
-        return {"error": str(e)}
+        return {"error": str(e)}, history
 
 # Create Gradio interface
 demo = gr.Interface(
     fn=respond,
     inputs=[
         gr.Textbox(label="User Input"),
-        gr.State(),
+        gr.State(),  # Explicit state for history tracking
         gr.Textbox(value="You are a friendly medical assistant.", 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"),
     ],
-    outputs="json",
+    outputs=[
+        gr.Textbox(label="Model Response"),
+        gr.State(),  # Explicit state output
+    ],
 )
 
 if __name__ == "__main__":