Update app.py

app.py

@@ -53,22 +53,47 @@ def process_input(text, image=None):
     return decoded_output
 
 # Gradio Interface Setup
+# def demo():
+#     # Define Gradio input and output components
+#     text_input = gr.Textbox(label="Text Input", placeholder="Enter text here", lines=5)
+
+#     # Use type="pil" to work with PIL Image objects
+#     image_input = gr.Image(label="Upload an Image", type="pil")
+
+#     output = gr.Textbox(label="Model Output", lines=5)
+
+#     # Define the interface layout
+#     interface = gr.Interface(
+#         fn=process_input,
+#         inputs=[text_input, image_input],
+#         outputs=output,
+#         title="Llama 3.2 Multimodal Text-Image Analyzer",
+#         description="Upload an image and/or provide text for analysis using the Llama 3.2 Vision Model."
+#     )
+
+#     # Launch the demo
+#     interface.launch()
+
 def demo():
     # Define Gradio input and output components
     text_input = gr.Textbox(label="Text Input", placeholder="Enter text here", lines=5)
-
-    # Use type="pil" to work with PIL Image objects
     image_input = gr.Image(label="Upload an Image", type="pil")
-
     output = gr.Textbox(label="Model Output", lines=5)
 
+    # Add two examples for multimodal analysis
+    examples = [
+        ["The llama is ", "./examples/rococo.jpg"],
+        ["The cute hampster is wearing ", "./examples/weather_events.png"]
+    ]
+
     # Define the interface layout
     interface = gr.Interface(
         fn=process_input,
         inputs=[text_input, image_input],
         outputs=output,
+        examples=examples,
         title="Llama 3.2 Multimodal Text-Image Analyzer",
-        description="Upload an image and/or provide text for analysis using the Llama 3.2 Vision Model."
+        description="Upload an image and/or provide text for analysis using the Llama 3.2 Vision Model. You can also try out the provided examples.",
     )
 
     # Launch the demo