Seldon · Schema

Seldon Inference Response (Open Inference Protocol V2)

Schema for an inference response payload returned from a Seldon model endpoint following the Open Inference Protocol V2.

MLOpsMachine LearningModel ServingInferenceKubernetesAI OperationsDrift DetectionExplainabilityCanary DeploymentA/B TestingLLMOps

Properties

Name Type Description
id string Echoed request identifier, or a server-generated identifier.
model_name string The name of the model that produced this response.
model_version string The version of the model that produced this response.
outputs array List of output tensors returned by the model.
parameters object Optional response-level parameters.
View JSON Schema on GitHub

JSON Schema

seldon-inference-response.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/seldon/main/json-schema/seldon-inference-response.json",
  "title": "Seldon Inference Response (Open Inference Protocol V2)",
  "description": "Schema for an inference response payload returned from a Seldon model endpoint following the Open Inference Protocol V2.",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Echoed request identifier, or a server-generated identifier."
    },
    "model_name": {
      "type": "string",
      "description": "The name of the model that produced this response."
    },
    "model_version": {
      "type": "string",
      "description": "The version of the model that produced this response."
    },
    "outputs": {
      "type": "array",
      "description": "List of output tensors returned by the model.",
      "items": {
        "$ref": "#/$defs/InferenceTensor"
      },
      "minItems": 1
    },
    "parameters": {
      "type": "object",
      "description": "Optional response-level parameters.",
      "additionalProperties": true
    }
  },
  "required": ["model_name", "outputs"],
  "$defs": {
    "InferenceTensor": {
      "type": "object",
      "title": "InferenceTensor",
      "description": "A named tensor with shape, datatype, and data.",
      "properties": {
        "name": {
          "type": "string",
          "description": "The name of the output tensor."
        },
        "shape": {
          "type": "array",
          "description": "The shape of the tensor.",
          "items": {
            "type": "integer"
          }
        },
        "datatype": {
          "type": "string",
          "description": "The datatype of the tensor.",
          "enum": ["BOOL", "UINT8", "UINT16", "UINT32", "UINT64", "INT8", "INT16", "INT32", "INT64", "FP16", "FP32", "FP64", "BYTES", "STRING"]
        },
        "data": {
          "description": "The tensor data.",
          "oneOf": [
            { "type": "array" },
            { "type": "string" }
          ]
        },
        "parameters": {
          "type": "object",
          "additionalProperties": true
        }
      },
      "required": ["name", "shape", "datatype", "data"]
    }
  },
  "examples": [
    {
      "id": "req-001",
      "model_name": "iris-classifier",
      "model_version": "v1",
      "outputs": [
        {
          "name": "predict",
          "shape": [1],
          "datatype": "INT64",
          "data": [0]
        }
      ]
    }
  ]
}