Update app.py

app.py

@@ -61,13 +61,13 @@ def extract_frames(frame):
 
     return image_bgr
 
-def predict_answer(video,image, 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)
 
     
-    if image is not None:
+    if image:
         # Process as an image
         image = image.convert("RGB")
         image_tensor = model.image_preprocess(image)
@@ -81,7 +81,7 @@ def predict_answer(video,image, question):
         
         return tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()
         
-    elif video is not None:
+    elif video:
         # Process as a video
         frames = video_to_frames(video)
         answers = []
@@ -103,8 +103,7 @@ def predict_answer(video,image, question):
     else:
         return "Unsupported file type. Please upload an image or video."
         
-promt_cat_dog = """
-        Annotate this image with this schema:
+promt_cat_dog = """Annotate this image with this schema:
         {
         “description”: “Is there a cat in the image?”,
         “value”: “Cat”
@@ -148,7 +147,6 @@ promt_video = """
         """
 test_examples = [[None, "Images/cat_dog.jpeg", promt_cat_dog], 
             [None,"Images/bus_people.jpeg", promt_bus_people], 
-            ["videos/v1.mp4",None,promt_video],
             ["videos/v2.mp4",None,promt_video],
             ["videos/v3.mp4",None,promt_video]]