Update app.py

app.py

@@ -6,14 +6,9 @@ from src.video_model import describe_video
 from src.utils import parse_string, parse_annotations
 import os
 
-
 # --- Function to construct the final query --- 
 def process_video_and_questions(video, standing, hands, location, screen):
-    # Extract the video name (filename)
     video_name = os.path.basename(video)
-
-    
-    # Construct the query with the video name included
     query = f"Answer the questions from the video\n"
     additional_info = []
     if standing:
@@ -35,53 +30,34 @@ def process_video_and_questions(video, standing, hands, location, screen):
     final_query = query + " " + " ".join(additional_info)
     final_prompt = final_query + " " + end_query
     
-    # Assuming your describe_video function handles the video processing
     response = describe_video(video, final_prompt)
     final_response = f"<video_name>{video_name}</video_name>" + " \n" + response
 
     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')
+        '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)
-        
-    # if standing == False:
-    #     final_response = final_response.replace('standing: 1', 'standing: None')
-    # elif hands == False:
-    #     final_response  = final_response.replace('hands.free: 1', 'hands.free: None')
-    # elif location == False:
-    #     final_response  = final_response.replace('indoors: 1', 'indoors: None')
-    # elif screen == False:
-    #     final_response  = final_response.replace('screen.interaction_yes: 1', 'screen.interaction_yes: None')
-
     
     return final_response 
 
-
-
-
 def output_to_csv(final_response):
-    # Parse the string to get the content
     parsed_content = parse_string(final_response, ["video_name", "annotation"])
-    
-    # Extract video name (assuming there's only one video name)
     video_name = parsed_content['video_name'][0] if parsed_content['video_name'] else None
-    
-    # Convert the list of annotations into a dictionary
     annotations_dict = parse_annotations(parsed_content['annotation']) if parsed_content['annotation'] else {}
     
-    # Combine the video name and annotation dictionary into a single row
     df = pd.DataFrame([{'video_name': video_name, **annotations_dict}])
-
     
+    # Save the DataFrame as a CSV file
+    csv_file_path = f"{video_name}_annotations.csv"
+    df.to_csv(csv_file_path, index=False)
     
-    return df
-
+    return csv_file_path  # Return the path to the CSV file for download
 
 # Examples for the interface
 examples = [
@@ -98,14 +74,11 @@ examples = [
     ["videos/2016-01-28_0700_US_KNBC_Channel_4_News_at_11PM_629.56-633.99_in_the_future.mp4", True, False, False, True]
 ]
 
-# Title, description, and article for the interface
 title = "GSoC Super Raid Annotator"
 description = "Annotate Videos"
 article = "<p style='text-align: center'><a href='https://github.com/OpenBMB/MiniCPM-V' target='_blank'>Model GitHub Repo</a> | <a href='https://huggingface.co/openbmb/MiniCPM-V-2_6' target='_blank'>Model Page</a></p>"
 
-custom_theme = gr.themes.Soft(
-    primary_hue="red", 
-    secondary_hue="red")
+custom_theme = gr.themes.Soft(primary_hue="red", secondary_hue="red")
 
 with gr.Blocks(theme=custom_theme) as demo:
     gr.Markdown(f"# {title}")
@@ -124,16 +97,14 @@ with gr.Blocks(theme=custom_theme) as demo:
         
         with gr.Column():
             response = gr.Textbox(label="Video Description", show_label=True, show_copy_button=True)
-            csv_output = gr.DataFrame(label="CSV Output", headers=["video_name", "annotation"])
+            csv_output = gr.File(label="Download CSV", interactive=False)
     
-    # Event handling for the Submit button
     submit_btn.click(
         fn=process_video_and_questions,
         inputs=[video, standing, hands, location, screen],
         outputs=response
     )
     
-    # Event handling for the Generate CSV button
     generate_csv_btn.click(
         fn=output_to_csv,
         inputs=response,
@@ -142,4 +113,4 @@ with gr.Blocks(theme=custom_theme) as demo:
     
     gr.Examples(examples=examples, inputs=[video, standing, hands, location, screen])
     
-demo.launch(debug=False)
+demo.launch(debug=False)