Amazon Neptune Data Processing API

openapi: 3.1.0
info:
  title: Amazon Neptune Neptune Analytics ?Action=AddTagsToResource ?Action=AddTagsToResource Data Processing 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: Data Processing
  description: ML data processing job operations
paths:
  /ml/dataprocessing:
    post:
      operationId: createDataProcessingJob
      summary: Amazon Neptune Create an ML Data Processing Job
      description: Creates a new Neptune ML data processing job that exports and prepares graph data from Neptune for model training using Amazon SageMaker. The job reads data from Neptune and writes processed output to the specified S3 location.
      tags:
      - Data Processing
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateDataProcessingJobRequest'
      responses:
        '200':
          description: Data processing job created successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobCreatedResponse'
              examples:
                createDataProcessingJob200Example:
                  summary: Default createDataProcessingJob 200 response
                  x-microcks-default: true
                  value:
                    id: neptune-cluster-abc123
        '400':
          description: Bad request - invalid parameters.
        '500':
          description: Internal server error.
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
    get:
      operationId: listDataProcessingJobs
      summary: Amazon Neptune List Active Data Processing Jobs
      description: Returns a list of active Neptune ML data processing job IDs.
      tags:
      - Data Processing
      parameters:
      - name: maxItems
        in: query
        description: Maximum number of items to return (default 10, max 1024).
        schema:
          type: integer
          default: 10
          maximum: 1024
      - name: neptuneIamRoleArn
        in: query
        description: The ARN of the IAM role for Neptune access.
        schema:
          type: string
      responses:
        '200':
          description: Job list retrieved successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobListResponse'
              examples:
                listDataProcessingJobs200Example:
                  summary: Default listDataProcessingJobs 200 response
                  x-microcks-default: true
                  value:
                    ids:
                    - example-value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /ml/dataprocessing/{id}:
    get:
      operationId: getDataProcessingJobStatus
      summary: Amazon Neptune Get Data Processing Job Status
      description: Returns the status of a Neptune ML data processing job.
      tags:
      - Data Processing
      parameters:
      - name: id
        in: path
        required: true
        description: The unique identifier of the data processing job.
        schema:
          type: string
      - name: neptuneIamRoleArn
        in: query
        description: The ARN of the IAM role for Neptune access.
        schema:
          type: string
      responses:
        '200':
          description: Job status retrieved successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobStatusResponse'
              examples:
                getDataProcessingJobStatus200Example:
                  summary: Default getDataProcessingJobStatus 200 response
                  x-microcks-default: true
                  value:
                    status: available
                    id: neptune-cluster-abc123
                    processingJob:
                      name: my-neptune-cluster
                      arn: arn:aws:neptune:us-east-1:123456789012:db:neptune-cluster-1
                      status: available
                      outputLocation: example-value
                      failureReason: example-value
        '404':
          description: Job not found.
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
    delete:
      operationId: stopDataProcessingJob
      summary: Amazon Neptune Stop a Data Processing Job
      description: Stops a running Neptune ML data processing job. Optionally deletes all S3 artifacts when the clean parameter is set to true.
      tags:
      - Data Processing
      parameters:
      - name: id
        in: path
        required: true
        description: The unique identifier of the data processing job.
        schema:
          type: string
      - name: clean
        in: query
        description: Whether to delete all S3 artifacts when stopping.
        schema:
          type: boolean
          default: false
      - name: neptuneIamRoleArn
        in: query
        description: The ARN of the IAM role for Neptune access.
        schema:
          type: string
      responses:
        '200':
          description: Job stopped successfully.
        '404':
          description: Job not found.
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    JobListResponse:
      type: object
      properties:
        ids:
          type: array
          description: List of job IDs.
          items:
            type: string
    JobCreatedResponse:
      type: object
      properties:
        id:
          type: string
          description: The unique identifier for the created job.
    CreateDataProcessingJobRequest:
      type: object
      required:
      - inputDataS3Location
      - processedDataS3Location
      properties:
        id:
          type: string
          description: Unique identifier for the job (auto-generated UUID if omitted).
        inputDataS3Location:
          type: string
          description: S3 URI for the input data.
        processedDataS3Location:
          type: string
          description: S3 URI where processed output is written.
        previousDataProcessingJobId:
          type: string
          description: Job ID of a previous job for incremental processing.
        sagemakerIamRoleArn:
          type: string
          description: IAM role ARN for SageMaker execution.
        neptuneIamRoleArn:
          type: string
          description: IAM role ARN for Neptune access.
        processingInstanceType:
          type: string
          description: ML instance type (default auto-selected ml.r5 type).
        processingInstanceVolumeSizeInGB:
          type: integer
          description: Disk volume size in GB (default 0 means auto-selected).
        processingTimeOutInSeconds:
          type: integer
          description: Timeout in seconds (default 86400, i.e., 1 day).
          default: 86400
        modelType:
          type: string
          description: The type of model to prepare data for.
          enum:
          - heterogeneous
          - kge
        configFileName:
          type: string
          description: The data specification configuration file name.
          default: training-data-configuration.json
        subnets:
          type: array
          description: VPC subnet IDs for SageMaker processing.
          items:
            type: string
        securityGroupIds:
          type: array
          description: VPC security group IDs.
          items:
            type: string
        volumeEncryptionKMSKey:
          type: string
          description: KMS key for storage volume encryption.
        s3OutputEncryptionKMSKey:
          type: string
          description: KMS key for S3 output encryption.
        enableInterContainerTrafficEncryption:
          type: boolean
          description: Whether to enable inter-container traffic encryption.
          default: true
    JobStatusResponse:
      type: object
      properties:
        status:
          type: string
          description: The current status of the job.
        id:
          type: string
          description: The job identifier.
        processingJob:
          type: object
          properties:
            name:
              type: string
            arn:
              type: string
            status:
              type: string
            outputLocation:
              type: string
            failureReason:
              type: string
            cloudwatchLogUrl:
              type: string
  securitySchemes:
    aws_sigv4:
      type: apiKey
      name: Authorization
      in: header
      description: AWS Signature Version 4 authentication