e0f928f429
docker-compose.yml에 reranker 서비스 추가: - image: ghcr.io/huggingface/text-embeddings-inference:1.5 - MODEL_ID=BAAI/bge-reranker-v2-m3 - MAX_BATCH_TOKENS=8192, MAX_CONCURRENT_REQUESTS=4 - GPU 1개 할당 (RTX 4070 Ti Super, CUDA 13.0) - expose 80만 (host 노출 X, internal network 전용) - reranker_cache volume으로 모델 영속화 - fastapi가 depends_on 안 함 → 단독 시작 가능, reranker 없어도 fastapi 동작 (rerank_service가 RRF fallback) 다음 단계: - GPU에서 docker pull로 호환성 확인 - docker compose up -d reranker → warmup - config.yaml의 rerank.endpoint를 http://reranker:80/rerank로 갱신 (GPU 직접) - fastapi rebuild + 평가셋 측정 (rerank=true)
129 lines
3.2 KiB
YAML
129 lines
3.2 KiB
YAML
services:
|
|
postgres:
|
|
image: pgvector/pgvector:pg16
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
- ./migrations:/docker-entrypoint-initdb.d
|
|
environment:
|
|
POSTGRES_DB: pkm
|
|
POSTGRES_USER: pkm
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
|
|
ports:
|
|
- "15432:5432"
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U pkm"]
|
|
interval: 5s
|
|
timeout: 5s
|
|
retries: 5
|
|
restart: unless-stopped
|
|
|
|
kordoc-service:
|
|
build: ./services/kordoc
|
|
ports:
|
|
- "3100:3100"
|
|
volumes:
|
|
- ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents:ro
|
|
healthcheck:
|
|
test: ["CMD", "node", "-e", "fetch('http://localhost:3100/health').then(r=>{process.exit(r.ok?0:1)}).catch(()=>process.exit(1))"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 3
|
|
restart: unless-stopped
|
|
|
|
ollama:
|
|
image: ollama/ollama
|
|
volumes:
|
|
- ollama_data:/root/.ollama
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
ports:
|
|
- "127.0.0.1:11434:11434"
|
|
restart: unless-stopped
|
|
|
|
# Phase 1.3: bge-reranker-v2-m3 (TEI) — internal only, fastapi에서 reranker:80으로 호출
|
|
# fastapi가 depends_on 안 함 → 단독 시작 가능, 없어도 fastapi 동작 (rerank=false fallback)
|
|
reranker:
|
|
image: ghcr.io/huggingface/text-embeddings-inference:1.5
|
|
container_name: hyungi_document_server-reranker-1
|
|
expose:
|
|
- "80"
|
|
environment:
|
|
- MODEL_ID=BAAI/bge-reranker-v2-m3
|
|
- MAX_BATCH_TOKENS=8192
|
|
- MAX_CONCURRENT_REQUESTS=4
|
|
volumes:
|
|
- reranker_cache:/data
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|
|
|
|
ai-gateway:
|
|
build: ./gpu-server/services/ai-gateway
|
|
ports:
|
|
- "127.0.0.1:8081:8080"
|
|
environment:
|
|
- PRIMARY_ENDPOINT=http://100.76.254.116:8801/v1/chat/completions
|
|
- FALLBACK_ENDPOINT=http://ollama:11434/v1/chat/completions
|
|
- CLAUDE_API_KEY=${CLAUDE_API_KEY:-}
|
|
- DAILY_BUDGET_USD=${DAILY_BUDGET_USD:-5.00}
|
|
depends_on:
|
|
- ollama
|
|
restart: unless-stopped
|
|
|
|
fastapi:
|
|
build: ./app
|
|
ports:
|
|
- "8000:8000"
|
|
volumes:
|
|
- ${NAS_NFS_PATH:-/mnt/nas/Document_Server}:/documents
|
|
- ./config.yaml:/app/config.yaml:ro
|
|
- ./scripts:/app/scripts:ro
|
|
- ./logs:/app/logs
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
kordoc-service:
|
|
condition: service_healthy
|
|
env_file:
|
|
- credentials.env
|
|
environment:
|
|
- DATABASE_URL=postgresql+asyncpg://pkm:${POSTGRES_PASSWORD}@postgres:5432/pkm
|
|
- KORDOC_ENDPOINT=http://kordoc-service:3100
|
|
restart: unless-stopped
|
|
|
|
frontend:
|
|
build: ./frontend
|
|
ports:
|
|
- "3000:3000"
|
|
depends_on:
|
|
- fastapi
|
|
restart: unless-stopped
|
|
|
|
caddy:
|
|
image: caddy:2
|
|
ports:
|
|
- "8080:80"
|
|
volumes:
|
|
- ./Caddyfile:/etc/caddy/Caddyfile
|
|
- caddy_data:/data
|
|
depends_on:
|
|
- fastapi
|
|
- frontend
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
pgdata:
|
|
caddy_data:
|
|
ollama_data:
|
|
reranker_cache:
|