Update multi_video_app.py

multi_video_app.py

@@ -20,14 +20,14 @@ def save_to_csv(observations: List[Dict], output_dir: str = "outputs") -> str:
     
     with open(csv_file, mode='w', newline='') as file:
         writer = csv.writer(file)
-        writer.writerow(["video_name", "standing", "hands_free", "indoors", "screen_interaction_yes"])
+        writer.writerow(["video_name", "standing", "hands.free", "indoors", "screen.interaction_yes"])
         for observation in observations:
             writer.writerow([
                 observation['video_name'], 
                 observation['standing'], 
-                observation['hands_free'], 
+                observation['hands.free'], 
                 observation['indoors'], 
-                observation['screen_interaction_yes']
+                observation['screen.interaction_yes']
             ])
     
     return csv_file
@@ -57,24 +57,22 @@ def process_single_video(video_path: str, sitting, hands, location, screen) -> D
     final_prompt = final_query + " " + end_query
     
     # Assuming your describe_video function handles the video processing
-    response = describe_video(video_path, final_prompt)
-
-    try:
-        # Parse the annotations from the response
-        tags = ["annotation"]
-        parsed_data = parse_string(response, tags)
-        annotations_list = parsed_data.get("annotation", [])
-        annotations_dict = parse_annotations(annotations_list)
-        
-        return {
-            "video_name": video_name,
-            "standing": annotations_dict.get("standing", 'N/A'),
-            "hands_free": annotations_dict.get("hands.free", 'N/A'),
-            "indoors": annotations_dict.get("indoors", 'N/A'),
-            "screen_interaction_yes": annotations_dict.get("screen.interaction_yes", 'N/A'),
-        }
-    except Exception as e:
-        return {"error": f"An error occurred with {video_name}: {e}"}
+    final_response = describe_video(video_path, final_prompt)
+
+    conditions = {
+        'standing': (standing, 'standing: 1', 'standing: None'),
+        'hands': (hands, 'hands.free: 1', 'hands.free: None'),
+        'location': (location, 'indoors: 1', 'indoors: None'),
+        'screen': (screen, 'screen.interaction_yes: 1', 'screen.interaction_yes: None')
+    }
+    
+    for key, (condition, to_replace, replacement) in conditions.items():
+        if not condition:
+            final_response = final_response.replace(to_replace, replacement)
+
+    return final_response 
+    
+
 
 # Function to process all videos in a folder
 def process_multiple_videos(video_files: List[str], sitting, hands, location, screen):