edited output for the image

app.py

@@ -227,7 +227,7 @@ def process_and_query(text=None, image=None, audio=None):
         # If an image is provided, process it with OpenAI and use the response as the text query for Vectara
         if image is not None:
             text = process_image(image)
-            return text
+            return "**Summary:** "+text
         if audio is not None:
             text = process_speech(audio)
             # augment the prompt before feeding it to vectara
@@ -260,7 +260,7 @@ iface = gr.Interface(
     inputs=[
         gr.Textbox(label="Input Text"),
         gr.Image(label="Upload Image"),
-        gr.Audio(label="talk", type="filepath",
+        gr.Audio(label="talk in french", type="filepath",
                  sources="microphone", visible=True),
     ],
     outputs=[gr.Markdown(label="Output Text")],