Update app.py

app.py

@@ -133,7 +133,7 @@ def process_inputs(audio_filepath, image_filepath):
     output_filepath = "output_audio.mp3"
     voice_of_doctor = text_to_speech_with_elevenlabs(input_text=doctor_response, output_filepath=output_filepath)
 
-    return speech_to_text_output, doctor_response, output_filepath
+    return enhanced_prompt, encoded_image, speech_to_text_output, doctor_response, output_filepath
 
 
 # Create the interface
@@ -144,6 +144,8 @@ iface = gr.Interface(
         gr.Image(type="filepath")
     ],
     outputs=[
+        gr.Textbox(label="Prompt"),
+        gr.Textbox(label="Encoded Image"),
         gr.Textbox(label="Speech to Text"),
         gr.Textbox(label="Doctor's Response"),
         gr.Audio(label="Doctor's Voice")