lightspeed-stack/docker-compose.yaml at user-memory · jancervenka/lightspeed-stack · 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
services:
  # Mock MCP server for testing
  mcp-mock-server:
    build:
      context: .
      dockerfile: dev-tools/mcp-mock-server/Dockerfile
    container_name: mcp-mock-server
    ports:
      - "3000:3000"
    networks:
      - lightspeednet
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/"]
      interval: 5s
      timeout: 3s
      retries: 3
      start_period: 5s

  # Red Hat llama-stack distribution with FAISS
  llama-stack:
    build:
      context: .
      dockerfile: test.containerfile
    platform: linux/amd64
    container_name: llama-stack
    ports:
      - "8321:8321"  # Expose llama-stack on 8321 (adjust if needed)
    volumes:
      - ./run.yaml:/opt/app-root/run.yaml:z
      - ${GCP_KEYS_PATH:-./tmp/.gcp-keys-dummy}:/opt/app-root/.gcp-keys:ro
      - ./lightspeed-stack.yaml:/opt/app-root/lightspeed-stack.yaml:ro
      - llama-storage:/opt/app-root/src/.llama/storage
      - ./tests/e2e/rag:/opt/app-root/src/.llama/storage/rag:z
    environment:
      - BRAVE_SEARCH_API_KEY=${BRAVE_SEARCH_API_KEY:-}
      - TAVILY_SEARCH_API_KEY=${TAVILY_SEARCH_API_KEY:-}
      # OpenAI
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - E2E_OPENAI_MODEL=${E2E_OPENAI_MODEL:-gpt-4o-mini}
      # Azure Entra ID credentials (AZURE_API_KEY is passed via provider_data at request time)
      - TENANT_ID=${TENANT_ID:-}
      - CLIENT_ID=${CLIENT_ID:-}
      - CLIENT_SECRET=${CLIENT_SECRET:-}
      # RHAIIS
      - RHAIIS_URL=${RHAIIS_URL}
      - RHAIIS_PORT=${RHAIIS_PORT}
      - RHAIIS_API_KEY=${RHAIIS_API_KEY}
      - RHAIIS_MODEL=${RHAIIS_MODEL}
      # RHEL AI
      - RHEL_AI_URL=${RHEL_AI_URL}
      - RHEL_AI_PORT=${RHEL_AI_PORT}
      - RHEL_AI_API_KEY=${RHEL_AI_API_KEY}
      - RHEL_AI_MODEL=${RHEL_AI_MODEL}
      # VertexAI
      - GOOGLE_APPLICATION_CREDENTIALS=${GOOGLE_APPLICATION_CREDENTIALS:-}
      - VERTEX_AI_PROJECT=${VERTEX_AI_PROJECT:-}
      - VERTEX_AI_LOCATION=${VERTEX_AI_LOCATION:-}
      # WatsonX
      - WATSONX_BASE_URL=${WATSONX_BASE_URL:-}
      - WATSONX_PROJECT_ID=${WATSONX_PROJECT_ID:-}
      - WATSONX_API_KEY=${WATSONX_API_KEY:-}
      # Enable debug logging if needed
      - LLAMA_STACK_LOGGING=${LLAMA_STACK_LOGGING:-}
      # FAISS test
      - FAISS_VECTOR_STORE_ID=${FAISS_VECTOR_STORE_ID:-}
    networks:
      - lightspeednet
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8321/v1/health"]
      interval: 10s   # how often to run the check
      timeout: 5s    # how long to wait before considering it failed
      retries: 3      # how many times to retry before marking as unhealthy
      start_period: 15s # time to wait before starting checks

  lightspeed-stack:
    build:
      context: .
      dockerfile: Containerfile
    container_name: lightspeed-stack
    ports:
      - "8080:8080"
    volumes:
      - ./lightspeed-stack.yaml:/app-root/lightspeed-stack.yaml:z
      - ./tests/e2e/secrets/mcp-token:/tmp/mcp-secret-token:ro
      - ./tests/e2e/secrets/invalid-mcp-token:/tmp/invalid-mcp-secret-token:ro
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      # Azure Entra ID credentials (AZURE_API_KEY is obtained dynamically)
      - TENANT_ID=${TENANT_ID:-}
      - CLIENT_ID=${CLIENT_ID:-}
      - CLIENT_SECRET=${CLIENT_SECRET:-}
    depends_on:
        llama-stack:
          condition: service_healthy
        mcp-mock-server:
          condition: service_healthy
        mock-mcp:
          condition: service_healthy
    networks:
      - lightspeednet
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/liveness"]
      interval: 10s   # how often to run the check
      timeout: 5s    # how long to wait before considering it failed
      retries: 3      # how many times to retry before marking as unhealthy
      start_period: 5s # time to wait before starting checks

  # Mock JWKS server for RBAC E2E tests
  mock-jwks:
    build:
      context: ./tests/e2e/mock_jwks_server
      dockerfile: Dockerfile
    container_name: mock-jwks
    ports:
      - "8000:8000"
    networks:
      - lightspeednet
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
      interval: 5s
      timeout: 3s
      retries: 3
      start_period: 2s

  mock-mcp:
    build:
      context: ./tests/e2e/mock_mcp_server
      dockerfile: Dockerfile
    container_name: mock-mcp
    ports:
      - "3001:3001"
    networks:
      - lightspeednet
    healthcheck:
      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:3001/health')"]
      interval: 5s
      timeout: 3s
      retries: 3
      start_period: 2s


volumes:
  llama-storage:

networks:
  lightspeednet:
    driver: bridge