CodeRAG/docker-compose.yaml at main · Sebastiangmz/CodeRAG · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
# CodeRAG Docker Compose Configuration
# Usage: docker compose up

services:
  coderag:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: coderag
    restart: unless-stopped

    # NVIDIA GPU support
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

    ports:
      - "127.0.0.1:8000:8000"
      # The container still binds internally; host exposure stays loopback by default.

    environment:
      - DEBUG=false
      - SERVER_HOST=0.0.0.0
      - SERVER_PORT=8000
      - SERVER_LOG_LEVEL=info
      - MODEL_LLM_USE_4BIT=true
      - VECTORSTORE_PERSIST_DIRECTORY=/app/data/chroma_db
      - INGESTION_REPOS_CACHE_DIR=/app/data/repos

    volumes:
      # Persistent data storage
      - coderag_chroma:/app/data/chroma_db
      - coderag_repos:/app/data/repos
      - coderag_hf_cache:/app/data/hf_cache
      - coderag_torch_cache:/app/data/torch_cache

      # Optional: Mount configs for customization
      # - ./configs:/app/configs:ro

    healthcheck:
      test: ["CMD", "python", "-c", "import httpx; httpx.get('http://localhost:8000/health')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s  # Models take time to load

    # Resource limits
    mem_limit: 16g
    memswap_limit: 20g

volumes:
  coderag_chroma:
    name: coderag_chroma_db
  coderag_repos:
    name: coderag_repos_cache
  coderag_hf_cache:
    name: coderag_hf_cache
  coderag_torch_cache:
    name: coderag_torch_cache