Update app.py

app.py

@@ -3,20 +3,43 @@ from huggingface_hub import InferenceClient
 
 client = InferenceClient("thviet79/model-QA-medical")
 
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    # Assuming it's a question-answering model
-    response = client.question_answering(
-        inputs={"question": message, "context": system_message}
-    )
-    return response['answer']  # Extract the answer from the response
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    # Simplified version for testing
+    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})
+
+    # Temporary placeholder response for testing
+    response = f"Test response for message: {message}"
+    return response
+
 
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="Context for medical questions.", label="System message"),
+        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"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
     ],
 )