app.py

# Importing the requirements
import warnings
warnings.filterwarnings("ignore")

import gradio as gr
from src.video_model import describe_video


# Video and text inputs for the interface
video = gr.Video(label="Video")
query = gr.Textbox(label="Question", placeholder="Enter your question here")

# Output for the interface
response = gr.Textbox(label="Predicted answer", show_label=True, show_copy_button=True)

# Examples for the interface
examples = [
    [
        "videos/2016-01-01_0100_US_KNBC_Channel_4_News_1867.16-1871.38_now.mp4",
        "Here are some frames of a video. Describe this video in detail."
    ],
    [
        "videos/2016-01-01_0200_US_KNBC_Channel_4_News_1329.12-1333.29_tonight.mp4",
        "Here are some frames of a video. Describe this video in detail."
    ],
    [   "videos/2016-01-01_0830_US_KNBC_Tonight_Show_with_Jimmy_Fallon_725.45-729.76_tonight.mp4", 
        "Here are some frames of a video. Describe this video in detail."
    ]
]

# 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>"


# Launch the interface
interface = gr.Interface(
    fn=describe_video,
    inputs=[video, query],
    outputs=response,
    examples=examples,
    title=title,
    description=description,
    article=article,
    theme="Soft",
    allow_flagging="never",
)
interface.launch(debug=False)