raptor/docker-compose.sage.yml at main · gadievron/raptor · 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
64
65
# SAGE Memory Sidecar for RAPTOR
# Usage: docker compose -f docker-compose.sage.yml up -d
#
# Services:
#   sage    - SAGE consensus-validated memory (port 8090)
#   ollama  - Embedding model server (port 11435)
#
# Ports use non-standard mappings to avoid conflicts with local services.

services:
  ollama:
    image: ollama/ollama:0.21.0
    ports:
      - "11435:11434"
    volumes:
      - ollama_data:/root/.ollama
    healthcheck:
      test: ["CMD-SHELL", "ollama list || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
    restart: unless-stopped
    # Uncomment for GPU support:
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

  ollama-init:
    image: ollama/ollama:0.21.0
    depends_on:
      ollama:
        condition: service_healthy
    restart: "no"
    entrypoint: ["ollama", "pull", "nomic-embed-text"]
    environment:
      - OLLAMA_HOST=http://ollama:11434

  sage:
    image: ghcr.io/l33tdawg/sage:6.6.5
    ports:
      - "8090:8080"
    volumes:
      - sage_data:/root/.sage-gui
    depends_on:
      ollama:
        condition: service_healthy
    environment:
      - OLLAMA_URL=http://ollama:11434
      - REST_ADDR=0.0.0.0:8080
    healthcheck:
      # ghcr.io/l33tdawg/sage images ship with wget, not curl
      test: ["CMD-SHELL", "wget -qO- http://localhost:8080/health >/dev/null || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 10
      start_period: 30s
    restart: unless-stopped

volumes:
  ollama_data:
  sage_data: