Cognito/docker-compose.prod.yml at main · KoderFPV/Cognito · 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
version: "3.8"

services:
  # Next.js Application
  app:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: cognito-app
    ports:
      - "2137:2137"
    environment:
      - NODE_ENV=production
      - MONGODB_URI=mongodb://mongo:27017/cognito
    depends_on:
      - mongo
    restart: unless-stopped
    networks:
      - cognito-network
  mongo:
    image: mongo:7
    container_name: cognito-mongo
    ports:
      - "2138:27017"
    environment:
      - MONGO_INITDB_DATABASE=cognito
    volumes:
      - mongo-data:/data/db
    restart: unless-stopped

  weaviate:
    image: docker.io/semitechnologies/weaviate:1.30.1
    restart: on-failure:0
    ports:
      - "2139:8080"
      - "2140:2140"
    volumes:
      - ./weaviate-data:/var/lib/weaviate
    environment:
      LOG_LEVEL: "debug"
      QUERY_DEFAULTS_LIMIT: 1000
      PERSISTENCE_DATA_PATH: "/var/lib/weaviate"
      ENABLE_MODULES: "multi2vec-clip, backup-filesystem"
      BACKUP_FILESYSTEM_PATH: "/var/lib/weaviate/backups"
      CLUSTER_HOSTNAME: "node1"
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: "false"
      AUTHENTICATION_APIKEY_ENABLED: "true"
      AUTHENTICATION_APIKEY_ALLOWED_KEYS: "cognito-key,devs-key"
      AUTHENTICATION_APIKEY_USERS: "cognito,devs"
      AUTHORIZATION_RBAC_ENABLED: "true"
      AUTHORIZATION_RBAC_ROOT_USERS: "cognito"
      AUTHENTICATION_DB_USERS_ENABLED: "true"

  multi2vec-clip:
    image: cr.weaviate.io/semitechnologies/multi2vec-clip:sentence-transformers-clip-ViT-B-32-multilingual-v1

  text2vec-snowflake:
    image: kodercloud/snowflake-l-2-0-weaviate

  vllm-qwen3-vl:
    image: vllm/vllm-openai:latest
    volumes:
      - "./hfmodels:/root/.cache/huggingface"
    ports:
      - "2141:8000"
    command: >
      --host 0.0.0.0
      --port 8000
      --model Qwen/Qwen3-VL-8B-Instruct-FP8
      --enforce-eager
      --gpu-memory-utilization 0.75
      --max-model-len 3070
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["1"]
              capabilities: [gpu]

  vllm-qwen3:
    image: vllm/vllm-openai:latest
    volumes:
      - "./hfmodels:/root/.cache/huggingface"
    ports:
      - "2142:8000"
    command: >
      --host 0.0.0.0
      --port 8000
      --model Qwen/Qwen3-8B-FP8
      --enforce-eager
      --gpu-memory-utilization 0.50
      --max-model-len 3070
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["0"]
              capabilities: [gpu]

volumes:
  mongo-data:
  weaviate-data: