Update app.py

app.py

@@ -126,17 +126,35 @@ def gradio_predict(image, video, question, max_tokens):
     answer = predict_answer(image, video, question, max_tokens)
     return answer
 
-iface = gr.Interface(
-    fn=gradio_predict,
-    inputs=[
-        gr.Image(type="pil", label="Upload or Drag an Image"),
-        gr.Video(label="Upload your video here"),
-        gr.Textbox(label="Question", placeholder="e.g. Can you explain the slide?", scale=4),
-        gr.Slider(2, 500, value=25, label="Token Count", info="Choose between 2 and 500")],
-    outputs=gr.TextArea(label="Answer"),
-    # outputs=gr.Image(label="Output"),
-    title="Video/Image Viewer",
-    description="Upload an image or video to view it or extract frames from the video.",
-)
-
-iface.launch(debug=True)
+# iface = gr.Interface(
+#     fn=gradio_predict,
+#     inputs=[
+#         gr.Image(type="pil", label="Upload or Drag an Image"),
+#         gr.Video(label="Upload your video here"),
+#         gr.Textbox(label="Question", placeholder="e.g. Can you explain the slide?", scale=4),
+#         gr.Slider(2, 500, value=25, label="Token Count", info="Choose between 2 and 500")],
+#     outputs=gr.TextArea(label="Answer"),
+#     # outputs=gr.Image(label="Output"),
+#     title="Video/Image Viewer",
+#     description="Upload an image or video to view it or extract frames from the video.",
+# )
+
+# iface.launch(debug=True)
+
+
+with gr.Blocks() as app:
+    gr.Markdown("### Upload an Image or Video")
+    with gr.Row():
+        image = gr.Image(type="pil", label="Upload or Drag an Image")
+        video = gr.Video(label="Upload your video here")
+    with gr.Row():
+        with gr.Column():
+            question = gr.Textbox(label="Question", placeholder="e.g. Can you explain the slide?", lines=4)
+            tokens = gr.Slider(2, 500, value=25, label="Token Count", info="Choose between 2 and 500")
+        with gr.Column():
+            answer = gr.TextArea(label="Answer")
+    
+    btn = gr.Button("Predict")
+    btn.click(gradio_predict, inputs=[image, video, question, tokens], outputs=answer)
+
+app.launch(debug=True)