fix(infra): deploy Ollama to prod/staging compose + fix broken model-init recipe #759

Merged
marcel merged 8 commits from fix/issue-758-ollama-prod-compose into main 2026-06-06 20:30:35 +02:00
Showing only changes of commit db87a64cc0 - Show all commits

View File

@@ -17,7 +17,6 @@ System_Boundary(archiv, "Familienarchiv (Docker Compose)") {
ContainerDb(db, "Relational Database", "PostgreSQL 16", "Stores document metadata, persons, users, permission groups, tags, transcription blocks, audit log, and Spring Session data.")
ContainerDb(storage, "Object Storage", "MinIO (S3-compatible)", "Stores the actual document files (PDFs, scans). Backend uses a bucket-scoped service account (archiv-app), not MinIO root.")
Container(mc, "Bucket / Service-Account Init", "MinIO Client (mc)", "One-shot container on startup. Idempotent: creates the archive bucket, the archiv-app service account, and attaches the readwrite policy.")
Container(ollama, "Ollama", "Ollama / port 11434", "Local LLM inference server. Hosts qwen2.5:7b-instruct-q4_K_M for natural-language query parsing (NL Search). CPU-only; GPU not required.")
}
System_Boundary(observability, "Observability Stack (/opt/familienarchiv/docker-compose.observability.yml)") {
@@ -49,7 +48,6 @@ Rel(promtail, loki, "Pushes log streams", "HTTP/Loki push API")
Rel(backend, tempo, "Sends distributed traces via OTLP", "HTTP / OTLP / port 4318 (archiv-net)")
Rel(prometheus, backend, "Scrapes JVM + HTTP metrics", "HTTP 8081 /actuator/prometheus")
Rel(prometheus, ocr, "Scrapes OCR + http_* metrics", "HTTP 8000 /metrics")
Rel(backend, ollama, "NL search inference requests", "HTTP / REST / JSON")
Rel(prometheus, ollama, "Scrapes LLM request metrics", "HTTP 11434 /metrics")
Rel(grafana, prometheus, "Queries metrics", "HTTP 9090")
Rel(grafana, loki, "Queries logs", "HTTP 3100")