mirror of
https://github.com/suitenumerique/meet.git
synced 2026-10-24 05:22:43 +00:00
lebaudantoine
11e8470aa5
Sentry attaches stack frame locals to its events. When storing a transcript in S3 failed, the full transcript held in `data` and `transcript` was sent to Sentry. Keep locals for debugging, but scrub variables and nested dict keys known to hold transcripts, summaries, LLM prompts, participants' personal data or pre-signed URLs. Share the Sentry init between the API and the Celery worker, and never send request bodies.
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
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.