example-rag/docker-compose.yml at master · naeem-gitonga/example-rag · 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
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
services:
  minio:
    image: minio/minio
    ports:
      - "9000:9000"
      - "9001:9001"
    volumes:
      - minio-data:/data
    environment:
      MINIO_ROOT_USER: minioadmin
      MINIO_ROOT_PASSWORD: minioadmin
    command: server /data --console-address ":9001"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 30s
      timeout: 10s
      retries: 3

  minio-setup:
    image: minio/mc
    depends_on:
      - minio
    entrypoint: >
      /bin/sh -c "
      sleep 5;
      mc alias set local http://minio:9000 minioadmin minioadmin;
      mc mb local/lancedb --ignore-existing;
      echo 'Bucket created';
      "

  embedding:
    build:
      context: ./embedding
      dockerfile: Dockerfile
    ports:
      - "8001:8001"
    volumes:
      - ./embedding/models:/app/models
    environment:
      EMBEDDING_MODEL_PATH: /app/models/qwen3-embedding-0.6b
      EMBEDDING_PORT: "8001"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

  llm:
    build:
      context: ./llm
      dockerfile: Dockerfile
    ports:
      - "8004:8004"
    volumes:
      - ./llm/models:/app/models
    environment:
      LLM_MODEL_PATH: /app/models/qwen2.5-3b-instruct
      LLM_PORT: "8004"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

  ingestion:
    build:
      context: .
      dockerfile: ingestion/Dockerfile
    ports:
      - "8002:8080"
    depends_on:
      - minio
      - minio-setup
      - embedding
    environment:
      LANCEDB_URI: s3://lancedb/documents
      S3_ENDPOINT: http://minio:9000
      AWS_ACCESS_KEY_ID: minioadmin
      AWS_SECRET_ACCESS_KEY: minioadmin
      AWS_REGION: us-east-1
      EMBEDDING_SERVICE_URL: http://embedding:8001

  chat:
    build:
      context: .
      dockerfile: chat/Dockerfile
    ports:
      - "8003:8080"
    depends_on:
      - minio
      - minio-setup
      - embedding
      - mongo
    environment:
      LANCEDB_URI: s3://lancedb/documents
      S3_ENDPOINT: http://minio:9000
      AWS_ACCESS_KEY_ID: minioadmin
      AWS_SECRET_ACCESS_KEY: minioadmin
      AWS_REGION: us-east-1
      EMBEDDING_SERVICE_URL: http://embedding:8001
      LLM_SERVICE_URL: http://llm:8004
      MONGO_URI: mongodb://root:example@mongo:27017

  gateway:
    build:
      context: .
      dockerfile: gateway/Dockerfile
      target: dev
    ports:
      - "8080:8080"
    environment:
      GATEWAY_PORT: "8080"
      INGESTION_LAMBDA_ENDPOINT: http://ingestion:8080
      CHAT_LAMBDA_ENDPOINT: http://chat:8080
      LLM_SERVICE_URL: http://llm:8004
    volumes:
      - ./gateway:/app
      - /app/node_modules

  web:
    build:
      context: .
      dockerfile: web/Dockerfile.dev
      target: dev
    ports:
      - "3000:3000"
    depends_on:
      - gateway
      - ingestion
    environment:
      NEXT_PUBLIC_WS_URL: ws://192.168.2.17:8080/ws
      INGESTION_LAMBDA_URL: http://ingestion:8080/2015-03-31/functions/function/invocations
    volumes:
      - ./web:/app
      - ./shared:/shared
      - /app/node_modules
      - /app/.next

  mongo:
    image: mongo:8.2.3-noble
    container_name: example-rag-mongodb
    restart: unless-stopped
    ports:
      - "9002:27017"
    environment:
      MONGO_INITDB_ROOT_USERNAME: root
      MONGO_INITDB_ROOT_PASSWORD: example
      MONGO_INITDB_DATABASE: example_rag
    volumes:
      # Persistent data volume with 1GB limit (enforced at Docker level)
      - mongo_data:/data/db
      # Initialization script (runs on first startup when data dir is empty)
      - ./db/init-mongo.js:/docker-entrypoint-initdb.d/init-mongo.js:ro
      # MongoDB configuration
      - ./db/mongod.conf:/etc/mongod.conf:ro
    deploy:
      resources:
        limits:
          memory: 512M  # Limit container memory
    # MongoDB configuration loaded from mongod.conf
    command: ["mongod", "--config", "/etc/mongod.conf"]
    healthcheck:
      test: mongosh --eval 'db.runCommand("ping").ok' localhost:27017/example_rag --quiet
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 40s

volumes:
  minio-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: ${PWD}/minio-data
  mongo_data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: ${PWD}/db/data