From 9e33923f71cfd3aee271f543cd6f984e07c714dd Mon Sep 17 00:00:00 2001 From: Dirk Riemann Date: Sat, 18 Apr 2026 13:49:09 +0200 Subject: [PATCH] fix(compose): persist Surya + HF caches so rebuilds don't redownload models 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) --- docker-compose.yml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/docker-compose.yml b/docker-compose.yml index c3aa30b..9fbb6d8 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -24,8 +24,17 @@ services: - driver: nvidia count: 1 capabilities: [gpu] + volumes: + # Persist Surya (datalab) + HuggingFace model caches so rebuilds don't + # re-download ~1.5 GB of weights every time. + - ix_surya_cache:/root/.cache/datalab + - ix_hf_cache:/root/.cache/huggingface labels: infrastructure.web_url: "http://192.168.68.42:8994" backup.enable: "true" backup.type: "postgres" backup.name: "infoxtractor" + +volumes: + ix_surya_cache: + ix_hf_cache: