| services:
|
|
|
| vector-api:
|
| env_file:
|
| - .env
|
| build:
|
| context: .
|
| dockerfile: Dockerfile
|
| image: vector-search-api:v1.0.2
|
| container_name: vector-search-api
|
| ports:
|
| - "5200:5200"
|
| environment:
|
| - QDRANT_URL=http://localhost:6333
|
| - DEFAULT_COLLECTION=docs_2025
|
| - ALLOW_MODELS=all
|
| - API_KEY=
|
| - CORS_ALLOW_ORIGINS=*
|
| - DEVICE=auto
|
| - TORCH_NUM_THREADS=4
|
| - API_HOST=0.0.0.0
|
| - API_PORT=5200
|
| - HF_HOME=/app/.cache/huggingface
|
| - TRANSFORMERS_CACHE=/app/.cache/huggingface
|
| - SENTENCE_TRANSFORMERS_HOME=/app/.cache/huggingface
|
|
|
| - HF_HUB_OFFLINE=1
|
| - TRANSFORMERS_OFFLINE=1
|
| volumes:
|
| - ./app:/app/app:rw
|
| - ./models:/app/models:ro
|
| - ./config:/app/config:ro
|
| - model_cache:/app/.cache/huggingface
|
| - ./logs:/app/logs
|
| restart: unless-stopped
|
| healthcheck:
|
| test: ["CMD", "curl", "-f", "http://localhost:5200/health"]
|
| interval: 30s
|
| timeout: 10s
|
| retries: 5
|
|
|
| volumes:
|
| model_cache:
|
| driver: local |
