custom-ai-agent/docker-compose.cpu.yml at main · ervikassingh/custom-ai-agent · 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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
# Docker Compose configuration for CPU-only systems (no NVIDIA GPU)
# Usage: docker compose -f docker-compose.cpu.yml up --build

services:
  # PostgreSQL database for document storage
  postgres:
    image: postgres:16-alpine
    container_name: ai-agent-postgres
    ports:
      - "5432:5432"
    environment:
      - POSTGRES_USER=${DATABASE_USER:-postgres}
      - POSTGRES_PASSWORD=${DATABASE_PASSWORD:-postgres}
      - POSTGRES_DB=${DATABASE_NAME:-ai_agent}
    volumes:
      - postgres-data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${DATABASE_USER:-postgres} -d ${DATABASE_NAME:-ai_agent}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    restart: unless-stopped

  # Qdrant vector database for RAG
  qdrant:
    image: qdrant/qdrant:latest
    container_name: ai-agent-qdrant
    ports:
      - "6333:6333"
      - "6334:6334"
    volumes:
      - qdrant-data:/qdrant/storage
    healthcheck:
      test: ["CMD-SHELL", "bash -c 'exec 3<>/dev/tcp/localhost/6333'"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    restart: unless-stopped

  # Ollama service - runs the LLM (CPU mode)
  ollama:
    image: ollama/ollama:latest
    container_name: ai-agent-ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama-data:/root/.ollama
    healthcheck:
      test: ["CMD-SHELL", "ollama list || exit 1"]
      interval: 10s
      timeout: 10s
      retries: 10
      start_period: 30s
    restart: unless-stopped

  # Ollama model puller - pulls the required models (LLM + Embedding)
  ollama-pull:
    image: curlimages/curl:latest
    container_name: ai-agent-ollama-pull
    depends_on:
      ollama:
        condition: service_healthy
    environment:
      - OLLAMA_MODEL=${OLLAMA_MODEL:-llama3.2:1b}
      - EMBEDDING_MODEL=${EMBEDDING_MODEL:-nomic-embed-text}
    entrypoint:
      - sh
      - -c
      - |
        echo "Waiting for Ollama to be ready..." &&
        sleep 5 &&
        echo "Pulling LLM model: $$OLLAMA_MODEL..." &&
        curl -X POST http://ollama:11434/api/pull -d "{\"name\": \"$$OLLAMA_MODEL\"}" &&
        echo "Pulling embedding model: $$EMBEDDING_MODEL..." &&
        curl -X POST http://ollama:11434/api/pull -d "{\"name\": \"$$EMBEDDING_MODEL\"}" &&
        echo "All models pulled successfully!"
    restart: "no"

  # Backend service - NestJS API
  backend:
    build:
      context: .
      dockerfile: apps/backend/Dockerfile
    container_name: ai-agent-backend
    ports:
      - "3001:3001"
    environment:
      - NODE_ENV=production
      - PORT=3001
      - OLLAMA_BASE_URL=http://ollama:11434
      - OLLAMA_MODEL=${OLLAMA_MODEL:-llama3.2:1b}
      - EMBEDDING_MODEL=${EMBEDDING_MODEL:-nomic-embed-text}
      - SYSTEM_PROMPT=${SYSTEM_PROMPT:-}
      - CORS_ORIGINS=http://localhost:3000,http://frontend:3000
      # PostgreSQL
      - DATABASE_HOST=postgres
      - DATABASE_PORT=5432
      - DATABASE_USER=${DATABASE_USER:-postgres}
      - DATABASE_PASSWORD=${DATABASE_PASSWORD:-postgres}
      - DATABASE_NAME=${DATABASE_NAME:-ai_agent}
      # Qdrant
      - QDRANT_URL=http://qdrant:6333
      - QDRANT_COLLECTION=${QDRANT_COLLECTION:-documents}
    depends_on:
      ollama:
        condition: service_healthy
      postgres:
        condition: service_healthy
      qdrant:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "node", "-e", "fetch('http://localhost:3001/chat/health').then(r => process.exit(r.ok ? 0 : 1)).catch(() => process.exit(1))"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    restart: unless-stopped

  # Frontend service - Next.js app
  frontend:
    build:
      context: .
      dockerfile: apps/frontend/Dockerfile
      args:
        - NEXT_PUBLIC_API_URL=http://localhost:3001
    container_name: ai-agent-frontend
    ports:
      - "3000:3000"
    environment:
      - NODE_ENV=production
      - PORT=3000
    depends_on:
      backend:
        condition: service_healthy
    restart: unless-stopped

volumes:
  ollama-data:
    driver: local
  postgres-data:
    driver: local
  qdrant-data:
    driver: local