{
  "opencollection": "1.0.0",
  "info": {
    "name": "Triton Inference Server NVIDIA Triton Inference Server HTTP/REST CUDA Shared Memory Health API",
    "version": "2.0"
  },
  "items": [
    {
      "info": {
        "name": "Health",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Triton Inference Server Server Liveness Check",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/v2/health/live"
          },
          "docs": "Check if the Triton server is alive and able to receive requests. This is the KServe V2 standard liveness probe endpoint."
        },
        {
          "info": {
            "name": "Triton Inference Server Server Readiness Check",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/v2/health/ready"
          },
          "docs": "Check if the Triton server is ready to accept inference requests. The server is ready when all models that are loaded at startup are ready."
        },
        {
          "info": {
            "name": "Triton Inference Server Model Version Readiness Check",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/v2/models/:model_name/versions/:model_version/ready",
            "params": [
              {
                "name": "model_name",
                "value": "",
                "type": "path",
                "description": "Name of the model"
              },
              {
                "name": "model_version",
                "value": "",
                "type": "path",
                "description": "Version of the model"
              }
            ]
          },
          "docs": "Check if a specific version of a model is ready to accept inference requests."
        },
        {
          "info": {
            "name": "Triton Inference Server Model Readiness Check",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/v2/models/:model_name/ready",
            "params": [
              {
                "name": "model_name",
                "value": "",
                "type": "path",
                "description": "Name of the model"
              }
            ]
          },
          "docs": "Check if a model is ready to accept inference requests. Checks the default/latest version of the model."
        }
      ]
    }
  ],
  "bundled": true
}