bioCurator/docker-compose.memory.yml at main · sunitj/bioCurator · 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
# Memory Services Configuration
# Multi-modal memory backends for BioCurator agent system

services:
  # Knowledge Graph Database - Neo4j
  neo4j:
    image: neo4j:5.15-community
    container_name: biocurator-neo4j
    environment:
      - NEO4J_AUTH=neo4j/dev_password
      - NEO4J_PLUGINS=["apoc", "graph-data-science"]
      - NEO4J_dbms_security_procedures_unrestricted=apoc.*,gds.*
      - NEO4J_server_memory_heap_initial__size=512m
      - NEO4J_server_memory_heap_max__size=1G
      - NEO4J_server_memory_pagecache_size=512m
    ports:
      - "7474:7474" # HTTP
      - "7687:7687" # Bolt
    volumes:
      - neo4j-data:/data
      - neo4j-logs:/logs
      - neo4j-import:/var/lib/neo4j/import
      - neo4j-plugins:/plugins
    networks:
      - biocurator-network
    restart: unless-stopped
    healthcheck:
      test: [ "CMD", "cypher-shell", "--username", "neo4j", "--password", "dev_password", "RETURN 1" ]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 40s

  # Vector Database - Qdrant
  qdrant:
    # image: qdrant/qdrant:v1.7.3
    image: ghcr.io/qdrant/qdrant/qdrant:v1.15.4-unprivileged
    container_name: biocurator-qdrant
    environment:
      - QDRANT__SERVICE__HTTP_PORT=6333
      - QDRANT__SERVICE__GRPC_PORT=6334
    ports:
      - "6333:6333" # HTTP API
      - "6334:6334" # gRPC API
    volumes:
      - qdrant-data:/qdrant/storage
    networks:
      - biocurator-network
    restart: unless-stopped
    healthcheck:
      test: [ "CMD", "sh", "-c", "kill -0 1" ]
      interval: 15s
      timeout: 3s
      retries: 3
      start_period: 5s

  # Relational Database - PostgreSQL
  postgres:
    image: postgres:16-alpine
    container_name: biocurator-postgres
    environment:
      - POSTGRES_DB=biocurator_dev
      - POSTGRES_USER=postgres
      - POSTGRES_PASSWORD=postgres
      - POSTGRES_INITDB_ARGS=--encoding=UTF-8 --lc-collate=C --lc-ctype=C
    ports:
      - "5432:5432"
    volumes:
      - postgres-data:/var/lib/postgresql/data
      - ./scripts/sql:/docker-entrypoint-initdb.d
    networks:
      - biocurator-network
    restart: unless-stopped
    healthcheck:
      test: [ "CMD-SHELL", "pg_isready -U postgres -d biocurator_dev" ]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s

  # Time-series Database - InfluxDB (for agent performance metrics)
  influxdb:
    image: influxdb:2.7-alpine
    container_name: biocurator-influxdb
    environment:
      - DOCKER_INFLUXDB_INIT_MODE=setup
      - DOCKER_INFLUXDB_INIT_USERNAME=admin
      - DOCKER_INFLUXDB_INIT_PASSWORD=admin_password
      - DOCKER_INFLUXDB_INIT_ORG=biocurator
      - DOCKER_INFLUXDB_INIT_BUCKET=agent_metrics
      - DOCKER_INFLUXDB_INIT_RETENTION=30d
      - DOCKER_INFLUXDB_INIT_ADMIN_TOKEN=dev_token_12345
    ports:
      - "8086:8086"
    volumes:
      - influxdb-data:/var/lib/influxdb2
      - influxdb-config:/etc/influxdb2
    networks:
      - biocurator-network
    restart: unless-stopped
    healthcheck:
      test: [ "CMD-SHELL", "curl -f http://localhost:8086/health || exit 1" ]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s

networks:
  biocurator-network:
    external: true

volumes:
  # Neo4j volumes
  neo4j-data:
    driver: local
  neo4j-logs:
    driver: local
  neo4j-import:
    driver: local
  neo4j-plugins:
    driver: local

  # Qdrant volumes
  qdrant-data:
    driver: local

  # PostgreSQL volumes
  postgres-data:
    driver: local

  # InfluxDB volumes
  influxdb-data:
    driver: local
  influxdb-config:
    driver: local