app.py

import warnings
warnings.filterwarnings("ignore")
import gradio as gr
from src.video_model import describe_video  # Your video processing function
from src.text_processor import process_description  # Your text processing function

# --- Global variable to store the prediction ---
prediction = None

# --- Function to handle video processing ---
def process_video(video, sitting, hands, location, screen):
    global prediction  # Access the global prediction variable

    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?")
    if hands:
        additional_info.append("Is the subject holding any object in their hands, if so the hands are not free else they are free?")
    if location:
        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)
    prediction = describe_video(video, final_query)
    # Enable the "Process Text" button
    return gr.update(visible=True), prediction 

# --- Function to trigger text processing ---
def process_and_display_text():
    global prediction 
    json_response = process_description(prediction)
    return json_response

# ... (Gradio interface code) ... 

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 components
video_description = gr.Textbox(label="Video Description")
json_output = gr.JSON(label="JSON Output")
process_button = gr.Button("Process Text", visible=False) 

# Examples for the interface
examples = [
    ["videos/2016-01-01_0100_US_KNBC_Channel_4_News_1867.16-1871.38_now.mp4",],
    ["videos/2016-01-01_0200_US_KNBC_Channel_4_News_1329.12-1333.29_tonight.mp4",],
    ["videos/2016-01-01_0830_US_KNBC_Tonight_Show_with_Jimmy_Fallon_725.45-729.76_tonight.mp4",],
    ["videos/2016-01-01_0200_US_KOCE_The_PBS_Newshour_577.03-581.31_tonight.mp4"],
    ["videos/2016-01-01_1400_US_KTTV-FOX_Morning_News_at_6AM_1842.36-1846.68_this_year.mp4"],
    ["videos/2016-01-02_0735_US_KCBS_Late_Show_with_Stephen_Colbert_285.94-290.67_this_year.mp4"],
    ["videos/2016-01-13_2200_US_KTTV-FOX_The_Doctor_Oz_Show_1709.79-1714.17_this_month.mp4"],
    ["videos/2016-01-01_1400_US_KTTV-FOX_Morning_News_at_6AM_1842.36-1846.68_this_year.mp4"],
    ["videos/2016-01-01_1300_US_KNBC_Today_in_LA_at_5am_12.46-16.95_this_morning.mp4"],
    ["videos/2016-01-05_0200_US_KNBC_Channel_4_News_1561.29-1565.95_next_week.mp4"],
    ["videos/2016-01-28_0700_US_KNBC_Channel_4_News_at_11PM_629.56-633.99_in_the_future.mp4"]
]

# 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"
)

interface = gr.Interface(
    fn=process_video,  
    inputs=[video, sitting, hands, location, screen],
    outputs=[process_button, video_description], 
    examples=examples,
    title=title,
    description=description,
    article=article,
    theme=custom_theme,
    allow_flagging="never",
)

# Click event for the "Process Text" button
process_button.click(fn=process_and_display_text, outputs=json_output)

interface.launch(debug=False)