添加模型服务 (AddModelService)

POST zstack/v1/ai/model-services

Authorization: OAuth the-session-uuid

{
  "param": {
    "name": "text to text model service",
    "description": "This is text to text model service you can chose model",
    "yaml": "services:\n  - ports:\n      - 3000\n  name: qwen1.5-7b-chat:2b34xhrmqwhomjkd\n  livez: /livez\n  readyz: /readyz\n  serviceBootupTime: 30\nenv:\n  - key:value\n  - key:value\ndistro:\n  packages: vim,nfs-utils\npython:\n  requirements_txt: ./requirements.txt\n  index_url: https://pypi.tuna.tsinghua.edu.cn/simple\n  trusted_host: pypi.tuna.tsinghua.edu.cn",
    "modelCenterUuid": "modelCenterUuidExample",
    "installPath": "/opt/zstack/ai/model-services/qwen1.5-7b-chat",
    "requestCpu": 4,
    "requestMemory": 1024,
    "gpuComputeCapability": "7.5",
    "startCommand": "python3 app.py",
    "pythonVersion": "3.8.10",
    "condaVersion": "4.9.2",
    "type": "Endpoint",
    "source": "Other",
    "architectureImages": [
      {
        "cpuArchitecture": "X86_64",
        "vmImageUuid": "vmImageUuidX86Example",
        "dockerImage": "registry.example.com/x86_64/myimage:latest"
      },
      {
        "cpuArchitecture": "AARCH64",
        "vmImageUuid": "vmImageUuidAarchExample",
        "dockerImage": "registry.example.com/aarch64/myimage:latest"
      }
    ],
    "supportDistributed": false
  },
  "systemTags": [],
  "userTags": []
}

curl -H "Content-Type: application/json;charset=UTF-8" \
-H "Authorization: OAuth b86c9016b4f24953a9edefb53ca0678c" \
-X POST -d '{"param":{"name":"text to text model service","description":"This is text to text model service you can chose model","yaml":"services:\n  - ports:\n      - 3000\n  name: qwen1.5-7b-chat:2b34xhrmqwhomjkd\n  livez: /livez\n  readyz: /readyz\n  serviceBootupTime: 30\nenv:\n  - key:value\n  - key:value\ndistro:\n  packages: vim,nfs-utils\npython:\n  requirements_txt: ./requirements.txt\n  index_url: https://pypi.tuna.tsinghua.edu.cn/simple\n  trusted_host: pypi.tuna.tsinghua.edu.cn","modelCenterUuid":"modelCenterUuidExample","installPath":"/opt/zstack/ai/model-services/qwen1.5-7b-chat","requestCpu":4,"requestMemory":1024,"gpuComputeCapability":"7.5","startCommand":"python3 app.py","pythonVersion":"3.8.10","condaVersion":"4.9.2","type":"Endpoint","source":"Other","architectureImages":[{"cpuArchitecture":"X86_64","vmImageUuid":"vmImageUuidX86Example","dockerImage":"registry.example.com/x86_64/myimage:latest"},{"cpuArchitecture":"AARCH64","vmImageUuid":"vmImageUuidAarchExample","dockerImage":"registry.example.com/aarch64/myimage:latest"}],"supportDistributed":false}}' \
http://localhost:8080/zstack/v1/ai/model-services

{
  "inventory": {
    "name": "text to text model service",
    "description": "This is text to text model service you can chose model",
    "yaml": "model service parameters",
    "requestCpu": 4,
    "requestMemory": 1024
  }
}

AddModelServiceAction action = new AddModelServiceAction();
action.name = "text to text model service";
action.description = "This is text to text model service you can chose model";
action.yaml = "services:
  - ports:
      - 3000
  name: qwen1.5-7b-chat:2b34xhrmqwhomjkd
  livez: /livez
  readyz: /readyz
  serviceBootupTime: 30
env:
  - key:value
  - key:value
distro:
  packages: vim,nfs-utils
python:
  requirements_txt: ./requirements.txt
  index_url: https://pypi.tuna.tsinghua.edu.cn/simple
  trusted_host: pypi.tuna.tsinghua.edu.cn";
action.modelCenterUuid = "modelCenterUuidExample";
action.installPath = "/opt/zstack/ai/model-services/qwen1.5-7b-chat";
action.requestCpu = 4;
action.requestMemory = 1024;
action.gpuComputeCapability = "7.5";
action.startCommand = "python3 app.py";
action.pythonVersion = "3.8.10";
action.condaVersion = "4.9.2";
action.type = "Endpoint";
action.source = "Other";
action.architectureImages = asList([cpuArchitecture:X86_64, vmImageUuid:vmImageUuidX86Example, dockerImage:registry.example.com/x86_64/myimage:latest],[cpuArchitecture:AARCH64, vmImageUuid:vmImageUuidAarchExample, dockerImage:registry.example.com/aarch64/myimage:latest]);
action.supportDistributed = false;
action.sessionId = "b86c9016b4f24953a9edefb53ca0678c";
AddModelServiceAction.Result res = action.call();

AddModelServiceAction action = AddModelServiceAction()
action.name = "text to text model service"
action.description = "This is text to text model service you can chose model"
action.yaml = "services:
  - ports:
      - 3000
  name: qwen1.5-7b-chat:2b34xhrmqwhomjkd
  livez: /livez
  readyz: /readyz
  serviceBootupTime: 30
env:
  - key:value
  - key:value
distro:
  packages: vim,nfs-utils
python:
  requirements_txt: ./requirements.txt
  index_url: https://pypi.tuna.tsinghua.edu.cn/simple
  trusted_host: pypi.tuna.tsinghua.edu.cn"
action.modelCenterUuid = "modelCenterUuidExample"
action.installPath = "/opt/zstack/ai/model-services/qwen1.5-7b-chat"
action.requestCpu = 4
action.requestMemory = 1024
action.gpuComputeCapability = "7.5"
action.startCommand = "python3 app.py"
action.pythonVersion = "3.8.10"
action.condaVersion = "4.9.2"
action.type = "Endpoint"
action.source = "Other"
action.architectureImages = [[cpuArchitecture:X86_64, vmImageUuid:vmImageUuidX86Example, dockerImage:registry.example.com/x86_64/myimage:latest], [cpuArchitecture:AARCH64, vmImageUuid:vmImageUuidAarchExample, dockerImage:registry.example.com/aarch64/myimage:latest]]
action.supportDistributed = false
action.sessionId = "b86c9016b4f24953a9edefb53ca0678c"
AddModelServiceAction.Result res = action.call()