0ca78640ee
- Integrate ollama + ai-gateway into root docker-compose.yml (NVIDIA GPU runtime, single compose for all services) - Change NAS mount from SMB (NAS_SMB_PATH) to NFS (NAS_NFS_PATH) Default: /mnt/nas/Document_Server (fstab registered on GPU server) - Update config.yaml AI endpoints: primary → Mac mini MLX via Tailscale (100.76.254.116:8800) fallback/embedding/vision/rerank → ollama (same Docker network) gateway → ai-gateway (same Docker network) - Update credentials.env.example (remove GPU_SERVER_IP, add NFS path) - Mark gpu-server/docker-compose.yml as deprecated - Update CLAUDE.md network diagram and AI model config - Update architecture.md, deploy.md, devlog.md for GPU server as main - Caddyfile: auto_https off, HTTP only (TLS at upstream proxy) - Caddy port: 127.0.0.1:8080:80 (localhost only) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
37 lines
1.1 KiB
YAML
37 lines
1.1 KiB
YAML
# ═══════════════════════════════════════════════════
|
|
# 이 파일은 더 이상 사용하지 않음.
|
|
# 루트 docker-compose.yml로 통합됨 (2026-04-03).
|
|
# ═══════════════════════════════════════════════════
|
|
|
|
services:
|
|
ollama:
|
|
image: ollama/ollama
|
|
volumes:
|
|
- ollama_data:/root/.ollama
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
ports:
|
|
- "11434:11434"
|
|
restart: unless-stopped
|
|
|
|
ai-gateway:
|
|
build: ./services/ai-gateway
|
|
ports:
|
|
- "8080:8080"
|
|
environment:
|
|
- PRIMARY_ENDPOINT=${PRIMARY_ENDPOINT:-http://mac-mini:8800/v1/chat/completions}
|
|
- FALLBACK_ENDPOINT=http://ollama:11434/v1/chat/completions
|
|
- CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
|
|
- DAILY_BUDGET_USD=${DAILY_BUDGET_USD:-5.00}
|
|
depends_on:
|
|
- ollama
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
ollama_data:
|