-
Notifications
You must be signed in to change notification settings - Fork 0
Enhance video analyzer to detect slide transitions and generate timestamps for videos of slide decks #2
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
Co-authored-by: mrjf <[email protected]>
Co-authored-by: mrjf <[email protected]>
"No instructions provided. Please provide instructions to process the video.", | ||
); | ||
|
||
const RX = /^https:\/\/github.com\/user-attachments\/assets\/.+$/gim; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The video may be too big to fit in an issue, so we need to be able to fetch it from git large file storage.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We don't need to use issues at all for this flow. Take the file location in the repo as the arg.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Added Git LFS support to handle large video files. Both video analyzers now detect and properly download videos from Git LFS URLs including raw files, releases, and blob URLs, while maintaining backward compatibility with regular GitHub attachments. Added appropriate error handling and size monitoring for large files. Changes committed in 4f8e8a3.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Updated the slide deck annotator to accept a direct file path parameter instead of extracting videos from GitHub issues. The script now takes video_file_path
as a parameter and processes the video file directly from the repository location, removing the dependency on issues entirely. Changes committed in 6e12cb6.
Co-authored-by: mrjf <[email protected]>
Co-authored-by: mrjf <[email protected]>
…tracting from issues Co-authored-by: mrjf <[email protected]>
Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details. Warning Firewall rules blocked me from connecting to one or more addressesI tried to connect to the following addresses, but was blocked by firewall rules:
If you need me to access, download, or install something from one of these locations, you can either:
|
This PR implements a new slide deck annotator that detects slide transitions in presentation videos and generates structured timestamps with confidence scores.
New Features
Slide Transition Detection
Structured JSON Output
The new annotator generates structured JSON matching the requested format:
Implementation Details
New Files
genaisrc/action-video-slide-deck-annotator.genai.mts
- Main slide detection script.github/workflows/genai-video-slide-deck-annotator.yml
- Workflow for slide analysisentrypoint.sh
- Configurable Docker entrypointEnhanced Configurability
script
parameter toaction.yml
for selecting between analyzersUsage
Use the slide deck annotator by specifying the script parameter:
Key Benefits
The implementation maintains full backward compatibility while adding powerful new slide analysis capabilities.
Fixes #1.
Warning
Firewall rules blocked me from connecting to one or more addresses
I tried to connect to the following addresses, but was blocked by firewall rules:
cdn.sheetjs.com
npm install
(dns block)npm ci
(dns block)If you need me to access, download, or install something from one of these locations, you can either:
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.