mirror of
https://github.com/suitenumerique/meet.git
synced 2026-07-27 20:29:09 +00:00
lebaudantoine
309c532811
Screen recording are MP4 files containing video) The current approach is suboptimal: the microservice will later be updated to extract audio paths from video, which can be heavy to send to the Whisper service. This implementation is straightforward, but the notification service is now handling many responsibilities through conditional logic. A refactor with a more configurable approach (mapping attributes to processing steps via settings) would be cleaner and easier to maintain. For now, this works; further improvements can come later. I follow the KISS principle, and try to make this new feature implemented with the lesser impact on the codebase. This isn’t perfect.
Experimental Stack
This is an experimental part of the stack. It currently lacks proper observability, unit tests, and other production-grade features. This serves as the base for AI features in Visio.
How it works
Please refer to the Recording feature documentation and the Transcription feature documentation.
How to develop
(To develop locally follow the instructions on developing La Suite Meet locally)
From the root of the project:
make bootstrap
Configure your env values in env.d/summary to properly set up WhisperX and the LLM API you will call.
make run
When the stack is up, configure the MinIO webhook
(TODO: add this step to make bootstrap)
make minio-webhook-setup
If you want to develop on the Celery workers with hot reloading, run:
docker compose watch celery-summary-transcribe celery-summary-summarize
Celery workers will hot reload on any change.