Update app.py

app.py

@@ -1,11 +1,13 @@
+# --- main.py (your Gradio app file) ---
 import warnings
 warnings.filterwarnings("ignore")
 import gradio as gr
-from src.video_model import describe_video  # Assuming this function processes the video and query
+from src.video_model import describe_video  # Your video processing function
+from src.text_processor import process_description
 
-# --- Function to construct the final query --- 
-def process_video_and_questions(video, sitting, hands, location, screen):
-    query = "Describe this video in detail and answer the questions"
+# --- Function to handle both video and text processing ---
+def process_video_and_get_json(video, sitting, hands, location, screen):
+    query = "Describe this video in detail and answer the questions."
     additional_info = []
     if sitting:
         additional_info.append("Is the subject in the video standing or sitting?")
@@ -15,23 +17,23 @@ def process_video_and_questions(video, sitting, hands, location, screen):
         additional_info.append("Is the subject present indoors or outdoors?")
     if screen:
         additional_info.append("Is the subject interacting with a screen in the background by facing the screen?")
-    
+
     final_query = query + " " + " ".join(additional_info)
-    # Assuming your describe_video function handles the video processing
-    response = describe_video(video, final_query) 
-    return response
 
-# Video and text inputs for the interface
-video = gr.Video(label="Video")
+    video_description = describe_video(video, final_query)
+    json_response = process_description(video_description)
+
+    return video_description, json_response 
 
-# Options as checkboxes
+# --- Gradio Interface --- 
+video = gr.Video(label="Video")
 sitting = gr.Checkbox(label="Sitting/Standing")
 hands = gr.Checkbox(label="Hands Free/Not Free")
 location = gr.Checkbox(label="Indoors/Outdoors")
 screen = gr.Checkbox(label="Screen Interaction")
 
-# Output for the interface
-response = gr.Textbox(label="Predicted answer", show_label=True, show_copy_button=True)
+video_description = gr.Textbox(label="Video Description", show_label=True, show_copy_button=True)
+json_output = gr.JSON(label="JSON Output") 
 
 # Examples for the interface
 examples = [
@@ -53,17 +55,15 @@ 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(
-    # Set the primary hue of the Soft theme to your red color
     primary_hue="red", 
-    secondary_hue="red")
+    secondary_hue="red"
+)
 
-# Launch the interface
 interface = gr.Interface(
-    fn=process_video_and_questions, # Updated function to handle the query construction
-    inputs=[video, sitting, hands, location, screen], 
-    outputs=response,
+    fn=process_video_and_get_json, 
+    inputs=[video, sitting, hands, location, screen],
+    outputs=[video_description, json_output], 
     examples=examples,
     title=title,
     description=description,