infinite-context/docker-compose.yml at master · Lumi-node/infinite-context · 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
# Infinite Context - Complete Local Setup
#
# Start everything:  docker-compose up -d
# Chat:              docker-compose exec infinite-context infinite-context chat
# Benchmark:         docker-compose exec infinite-context infinite-context bench
#
# This gives you:
#   - Ollama running with your chosen model
#   - Infinite Context CLI ready to use
#   - Persistent memory storage

version: '3.8'

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    # GPU support (uncomment for NVIDIA)
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: all
    #           capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 10s
      timeout: 5s
      retries: 5

  infinite-context:
    build: .
    container_name: infinite-context
    depends_on:
      ollama:
        condition: service_healthy
    environment:
      - OLLAMA_HOST=http://ollama:11434
    volumes:
      - memory_data:/app/memory
    stdin_open: true
    tty: true
    command: >
      sh -c "
        echo 'Waiting for Ollama...' &&
        sleep 5 &&
        echo 'Pulling gemma3:1b model...' &&
        curl -s http://ollama:11434/api/pull -d '{\"name\":\"gemma3:1b\"}' &&
        echo 'Ready! Run: docker-compose exec infinite-context infinite-context chat' &&
        tail -f /dev/null
      "

volumes:
  ollama_data:
    name: infinite-context-ollama
  memory_data:
    name: infinite-context-memory