Update app.py

app.py

@@ -61,7 +61,7 @@ def extract_frames(frame):
 
     return image_bgr
 
-def predict_answer(image, video, question):
+def predict_answer(video,image, question):
 
     text = f"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: <image>\n{question}? ASSISTANT:"
     input_ids = tokenizer(text, return_tensors='pt').input_ids.to(device)
@@ -153,8 +153,8 @@ test_examples = [[None, "Images/cat_dog.jpeg", promt_cat_dog],
             ["videos/v3.mp4",None,promt_video]]
 
 
-def gradio_predict(image, video, question):
-    answer = predict_answer(image, video, question)
+def gradio_predict(video,image, question):
+    answer = predict_answer(video,image, question)
     return answer
 
 css = """