Update app.py

app.py

@@ -6,32 +6,27 @@ import gradio as gr
 # Suppress TensorFlow logs
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
-# Load the model
-model_path = 'doctor_ai_model.h5'  # Change to your model file
+# Load your model
+model_path = 'docctor_ai_model.h5'  # Change this to your actual model path
 model = keras.models.load_model(model_path)
 
-def predict(input_data):
-    # Convert input to tensor
-    input_tensor = tf.convert_to_tensor(input_data)
-
-    # Ensure the input shape is correct
-    if input_tensor.shape[1] != 27:  # Adjust based on your input shape
-        return "Input data must have shape: (None, 27)"
-    
-    # Expand dimensions for the model
-    input_tensor = tf.expand_dims(input_tensor, axis=0)
+def chatbot(input_text):
+    # Preprocess the input if needed, for example, converting it to the right shape
+    input_tensor = tf.convert_to_tensor([[float(i) for i in input_text.split()]])  # Adjust based on your model's expected input
 
     # Make prediction
     prediction = model.predict(input_tensor)
-    predicted_class = tf.argmax(prediction, axis=1).numpy().tolist()
-    
-    return predicted_class
+    response = prediction[0]  # This might need adjustment based on your model output
+
+    return response  # Return the chatbot's response
 
 # Create Gradio interface
 iface = gr.Interface(
-    fn=predict,
-    inputs=gr.Dataframe(type='numpy', label='Input Data (should have shape (None, 27))'),
-    outputs='json'
+    fn=chatbot,
+    inputs=gr.Textbox(label="User Input", placeholder="Type your message here..."),
+    outputs=gr.Textbox(label="Chatbot Response"),
+    title="AI Chatbot",
+    description="This is a chatbot powered by your model. Type a message to get a response!"
 )
 
 # Launch the Gradio app