Update app.py

app.py

@@ -4,6 +4,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import cv2
 import numpy as np
+import ast
 
 
 # # Ensure GPU usage if available
@@ -100,8 +101,8 @@ def predict_answer(image, video, question, max_tokens=100):
         # Process as a video
         frames = video_to_frames(video)
         answers = []
-        for frame in frames:
-            image = extract_frames(frame)
+        for i in range(len(frames)):
+            image = extract_frames(frames[i])
             image_tensor = model.image_preprocess([image])
             
             # Generate the answer
@@ -113,7 +114,7 @@ def predict_answer(image, video, question, max_tokens=100):
             
             answer = tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()
             answers.append(answer)
-        return answers
+        return ast.literal_eval(answers[0])
         
     else:
         return "Unsupported file type. Please upload an image or video."