fix(compose): persist Surya + HF model caches #38

Merged
goldstein merged 1 commit from fix/cache-volumes into main 2026-04-18 11:49:25 +00:00
Owner

Name-mounted volumes so rebuilds don't re-download 1.4 GB from HuggingFace.

Name-mounted volumes so rebuilds don't re-download 1.4 GB from HuggingFace.
goldstein added 1 commit 2026-04-18 11:49:22 +00:00
fix(compose): persist Surya + HF caches so rebuilds don't redownload models
All checks were successful
tests / test (push) Successful in 2m1s
tests / test (pull_request) Successful in 1m18s
9e33923f71
First /healthz call on a fresh container triggers Surya to fetch the
text-recognition (1.34 GB) and detection (73 MB) models from HuggingFace.
Without a volume they land in the container fs and vanish on every
rebuild, which is every deploy.

Mount named volumes for /root/.cache/datalab (Surya) and
/root/.cache/huggingface. Rebuild now keeps /healthz warm.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
goldstein merged commit f6ce97d7fd into main 2026-04-18 11:49:25 +00:00
Sign in to join this conversation.
No reviewers
No labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference: goldstein/infoxtractor#38
No description provided.