llm-rag-example/docker-compose.yml at master · rushan-zagidullin/llm-rag-example · 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
version: '3.8'

services:
  # PostgreSQL with pgvector extension
  postgres:
    image: pgvector/pgvector:pg16
    container_name: postgres-pgvector
    restart: unless-stopped
    environment:
      POSTGRES_USER: postgres
      POSTGRES_PASSWORD: postgres
      POSTGRES_DB: rag_db
    logging:
      options:
        max-size: 10m
        max-file: "3"
    ports:
      - "6432:5432"
    volumes:
      - ./postgres/data:/var/lib/postgresql/data
      - ./postgres/scripts:/docker-entrypoint-initdb.d
    healthcheck:
      test: "pg_isready -U postgres -d rag_db"
      interval: 2s
      timeout: 5s
      retries: 5
    networks:
      - rag-net
    deploy:
      resources:
        limits:
          memory: 2G
        reservations:
          memory: 1G

  # Ollama service (CPU-only for laptop)
  ollama:
    image: ollama/ollama:latest
    container_name: ollama-service
    restart: unless-stopped
    ports:
      - "11431:11434"
    volumes:
      - ./ollama:/root/.ollama
    entrypoint: "/bin/sh -c"
    command: |
      "ollama serve &
      sleep 2 &&
      ollama pull gemma3:4b-it-q4_K_M &&
      ollama pull mxbai-embed-large:latest
      wait"
    networks:
      - rag-net
    deploy:
      resources:
        limits:
          memory: 8G  # Ollama will use up to 8GB for models
        reservations:
          memory: 4G
networks:
  rag-net:
    driver: bridge
    name: rag-network