9e97687d0f
All checks were successful
CI / Unit & Component Tests (pull_request) Successful in 3m18s
CI / OCR Service Tests (pull_request) Successful in 22s
CI / Backend Unit Tests (pull_request) Successful in 3m55s
CI / fail2ban Regex (pull_request) Successful in 51s
CI / Semgrep Security Scan (pull_request) Successful in 22s
CI / Compose Bucket Idempotency (pull_request) Successful in 1m8s
NL search recovered after deploy but went 503 again after a few minutes:
Ollama unloads the model after its default ~5 min keep-alive, so the next
query cold-loads the 4.7 GB model and exceeds the backend's 30s read
timeout (ResourceAccessException -> SMART_SEARCH_UNAVAILABLE). Warm
inference is ~18s; the cold load after idle is what timed out.
- docker-compose.{prod,yml}: set OLLAMA_KEEP_ALIVE=-1 on the ollama
service so the model stays resident and never pays a cold-load penalty
during normal operation (verified on staging: `ollama ps` -> UNTIL
"Forever"; host has 47 GB free).
- application.yaml: raise app.ollama.timeout-seconds 30 -> 60 so the one
unavoidable cold load (first query after an Ollama restart, before the
model is pinned) completes instead of timing out.
Refs #758
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
11 KiB
11 KiB