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_0000_US_KNBC_The_Ellen_DeGeneres_Show_91.07-95.45_today.mp4",
        "Here are some frames of a video. Describe this video in detail.",
    ],
    [
        "./videos/videos/2016-01-01_0100_UK_KCET_BBC_World_News_America_218.99-223.26_ago.mp4",
        "Here are some frames of a video. Describe this video in detail.",
    ],
    ["  ./videos/2016-01-01_0100_US_KNBC_Channel_4_News_1877.19-1881.53_now.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 = "Gradio Demo for the MiniCPM-V 2.6 Vision Language Understanding and Generation model. This model can answer questions about videos in natural language. To use it, simply upload your video, type a question, and click 'submit', or click one of the examples to load them. Read more at the links below."
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)