Amazon Neptune Inference Endpoints API

openapi: 3.1.0
info:
  title: Amazon Neptune Neptune Analytics ?Action=AddTagsToResource ?Action=AddTagsToResource Inference Endpoints API
  description: Neptune Analytics is a memory-optimized graph database engine for analytics, providing optimized graph analytic algorithms, low-latency queries, and vector search capabilities within graph traversals. This API provides management operations for Neptune Analytics graph resources including creating, managing, and querying graph databases optimized for analytical workloads.
  version: '2023-11-29'
  contact:
    name: Amazon Web Services
    url: https://docs.aws.amazon.com/neptune-analytics/latest/userguide/what-is-neptune-analytics.html
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0
servers:
- url: https://neptune-graph.{region}.amazonaws.com
  description: Neptune Analytics control plane regional endpoint
  variables:
    region:
      default: us-east-1
      description: AWS region
security:
- aws_sigv4: []
tags:
- name: Inference Endpoints
  description: ML inference endpoint management operations
paths:
  /ml/endpoints:
    post:
      operationId: createInferenceEndpoint
      summary: Amazon Neptune Create an ML Inference Endpoint
      description: Creates a new Neptune ML inference endpoint backed by Amazon SageMaker. The endpoint can be used to make real-time predictions on graph data using a trained model. Can also be used to update an existing endpoint by setting the update parameter to true.
      tags:
      - Inference Endpoints
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateInferenceEndpointRequest'
      responses:
        '200':
          description: Inference endpoint created successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EndpointCreatedResponse'
              examples:
                createInferenceEndpoint200Example:
                  summary: Default createInferenceEndpoint 200 response
                  x-microcks-default: true
                  value:
                    id: neptune-cluster-abc123
        '400':
          description: Bad request - invalid parameters.
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
    get:
      operationId: listInferenceEndpoints
      summary: Amazon Neptune List ML Inference Endpoints
      description: Returns a list of active Neptune ML inference endpoint IDs.
      tags:
      - Inference Endpoints
      parameters:
      - name: maxItems
        in: query
        schema:
          type: integer
          default: 10
          maximum: 1024
      - name: neptuneIamRoleArn
        in: query
        schema:
          type: string
      responses:
        '200':
          description: Endpoint list retrieved successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EndpointListResponse'
              examples:
                listInferenceEndpoints200Example:
                  summary: Default listInferenceEndpoints 200 response
                  x-microcks-default: true
                  value:
                    ids:
                    - example-value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /ml/endpoints/{id}:
    get:
      operationId: getInferenceEndpointStatus
      summary: Amazon Neptune Get ML Inference Endpoint Status
      description: Returns the status of a Neptune ML inference endpoint.
      tags:
      - Inference Endpoints
      parameters:
      - name: id
        in: path
        required: true
        description: The unique identifier of the inference endpoint.
        schema:
          type: string
      - name: neptuneIamRoleArn
        in: query
        schema:
          type: string
      responses:
        '200':
          description: Endpoint status retrieved successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EndpointStatusResponse'
              examples:
                getInferenceEndpointStatus200Example:
                  summary: Default getInferenceEndpointStatus 200 response
                  x-microcks-default: true
                  value:
                    status: available
                    id: neptune-cluster-abc123
                    endpoint:
                      name: my-neptune-cluster
                      arn: arn:aws:neptune:us-east-1:123456789012:db:neptune-cluster-1
                      status: available
                    endpointConfig: {}
                    outputLocation: example-value
        '404':
          description: Endpoint not found.
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
    delete:
      operationId: deleteInferenceEndpoint
      summary: Amazon Neptune Delete an ML Inference Endpoint
      description: Deletes a Neptune ML inference endpoint. Optionally cleans up all related S3 artifacts.
      tags:
      - Inference Endpoints
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
      - name: clean
        in: query
        description: Whether to delete all related S3 artifacts.
        schema:
          type: boolean
          default: false
      - name: neptuneIamRoleArn
        in: query
        schema:
          type: string
      responses:
        '200':
          description: Endpoint deleted successfully.
        '404':
          description: Endpoint not found.
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    EndpointStatusResponse:
      type: object
      properties:
        status:
          type: string
        id:
          type: string
        endpoint:
          type: object
          properties:
            name:
              type: string
            arn:
              type: string
            status:
              type: string
        endpointConfig:
          type: object
        outputLocation:
          type: string
    CreateInferenceEndpointRequest:
      type: object
      properties:
        id:
          type: string
          description: Unique identifier for the endpoint (auto-generated timestamped name if omitted).
        mlModelTrainingJobId:
          type: string
          description: Job ID from a completed training job.
        mlModelTransformJobId:
          type: string
          description: Job ID from a completed transform job.
        update:
          type: boolean
          description: Whether this is an update to an existing endpoint.
          default: false
        neptuneIamRoleArn:
          type: string
        modelName:
          type: string
          description: The model type.
          enum:
          - rgcn
          - kge
          - transe
          - distmult
          - rotate
        instanceType:
          type: string
          description: ML instance type for the inference endpoint.
          default: ml.m5.xlarge
        instanceCount:
          type: integer
          description: Minimum number of EC2 instances to deploy.
          default: 1
        volumeEncryptionKMSKey:
          type: string
    EndpointCreatedResponse:
      type: object
      properties:
        id:
          type: string
          description: The unique identifier for the created endpoint.
    EndpointListResponse:
      type: object
      properties:
        ids:
          type: array
          items:
            type: string
  securitySchemes:
    aws_sigv4:
      type: apiKey
      name: Authorization
      in: header
      description: AWS Signature Version 4 authentication