feat(infra): Ollama Docker Compose service for NL search (#737) #749

Merged
marcel merged 15 commits from feat/issue-737-ollama-docker-compose into main 2026-06-06 15:19:06 +02:00
Showing only changes of commit e8f3004c4f - Show all commits

View File

@@ -72,6 +72,25 @@ VITE_SENTRY_DSN=
# Sentry/GlitchTip auth token for source map upload at build time (optional)
SENTRY_AUTH_TOKEN=
# NL search — Ollama LLM inference
# Leave APP_OLLAMA_BASE_URL empty to disable NL search (safe default for CX32 / CI).
# Set to http://ollama:11434 to enable. Requires CX42 (16 GB RAM) to run alongside OCR.
APP_OLLAMA_BASE_URL=http://ollama:11434
# CPU limit: 4.0 is safe on both CX32 (4 vCPUs) and CX42 (8 vCPUs).
# Raise to 7.5 on CX42 for full throughput.
OLLAMA_CPU_LIMIT=4.0
# Memory limit: requires CX42 (16 GB) to run alongside OCR.
# Reduce or set APP_OLLAMA_BASE_URL= on smaller hosts.
OLLAMA_MEM_LIMIT=8g
# Ollama API key — set on the Ollama service to restrict inference API access on archiv-net.
# Generate with: openssl rand -hex 32
# NOTE: Empirically verified that OLLAMA_API_KEY is NOT enforced in Ollama 0.6.5 (ADR-028 §7).
# Retained for forward compatibility. Leave empty for unauthenticated access.
OLLAMA_API_KEY=
# Production SMTP — uncomment and fill in to send real emails instead of catching them
# APP_BASE_URL=https://your-domain.example.com
# MAIL_HOST=smtp.example.com