mirror of https://github.com/suitenumerique/meet.git synced 2026-08-10 18:57:06 +00:00

Files

T

Florent Chehab 052d3c1b22 ✨(summary) report exception type in failure analytics

We know capture also the exception type that was raised
in failure analytics to provide more insights about what happened.

2026-07-24 10:14:59 +02:00

summary

✨(summary) report exception type in failure analytics

2026-07-24 10:14:59 +02:00

tests

✅(transcription) fix broken speaker assignment tests

2026-07-22 14:23:10 +02:00

Dockerfile

⬆️(summary) update ffmpeg to 8.1.2

2026-07-03 18:51:11 +02:00

pyproject.toml

🔖(minor) bump release to 1.24.0

2026-07-21 18:01:20 +02:00

README.md

📝(docs) add summarization documentation

2025-10-06 14:53:56 +02:00

README.md

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.