DataHub OpenAPI

openapi: 3.1.0
info:
  title: DataHub OpenAPI
  description: >-
    RESTful API endpoints for interacting with DataHub metadata using the OpenAPI
    standard. Provides endpoints for managing entities, querying relationships,
    retrieving timeline history, and emitting platform events. The OpenAPI
    endpoints offer the most powerful and flexible lower-level access to the
    DataHub metadata graph, supporting reads and writes of entity-aspect pairs,
    relationship traversal, versioned history queries, and batch operations.
    Recommended for advanced users who need programmatic control over the
    metadata graph beyond what the GraphQL API provides.
  version: '1.4.0'
  contact:
    name: DataHub Project
    url: https://datahubproject.io
  termsOfService: https://datahub.com/privacy-policy/
externalDocs:
  description: DataHub OpenAPI Usage Guide
  url: https://docs.datahub.com/docs/api/openapi/openapi-usage-guide
servers:
  - url: http://localhost:8080
    description: DataHub GMS Server (Local Quickstart)
  - url: http://localhost:9002
    description: DataHub Frontend Proxy (Local Quickstart)
tags:
  - name: Batch
    description: >-
      Batch operations for fetching multiple entities and their aspects in a
      single request. Supports version-specific retrieval and conditional
      writes.
  - name: Entities
    description: >-
      Read, write, and delete metadata entities in the DataHub metadata graph.
      The entities endpoints support upserting entity-aspect pairs, retrieving
      the latest aspects for a given entity, and performing soft or hard deletes
      on entities.
  - name: Platform
    description: >-
      Write metadata events using the standard platform format. Provides an
      alternative ingestion path for emitting metadata change proposals to the
      DataHub metadata graph.
  - name: Relationships
    description: >-
      Query the relationship graph to navigate connections between entities.
      Supports filtering by relationship type and traversal direction (incoming
      or outgoing) from a given entity URN.
  - name: Timeline
    description: >-
      Query the versioned history of entity aspects over time. Useful for
      tracking schema changes, documentation updates, and other temporal
      metadata modifications for a given entity.
security:
  - bearerAuth: []
paths:
  /entities/v1/:
    post:
      operationId: upsertEntities
      summary: DataHub Upsert entity aspects
      description: >-
        Create or update one or more entity aspects in the DataHub metadata
        graph. Supports upserting entity-aspect pairs where the entire DataHub
        metadata model is available for writing. Use the
        createEntityIfNotExists query parameter to conditionally create entities
        only if they do not already exist.
      tags:
        - Entities
      parameters:
        - $ref: '#/components/parameters/CreateEntityIfNotExists'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: array
              items:
                $ref: '#/components/schemas/EntityAspectRequest'
      responses:
        '200':
          description: Entities upserted successfully
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/EntityAspectResponse'
        '400':
          description: Invalid request body or schema validation failure
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication required or token is invalid
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
    delete:
      operationId: deleteEntities
      summary: DataHub Delete entities
      description: >-
        Delete one or more entities from the DataHub metadata graph. Supports
        both soft deletes (marking entities as removed while preserving
        metadata) and hard deletes (permanently removing all entity metadata).
        Soft delete is the default behavior.
      tags:
        - Entities
      parameters:
        - $ref: '#/components/parameters/Urns'
        - $ref: '#/components/parameters/SoftDelete'
      responses:
        '200':
          description: Entities deleted successfully
        '400':
          description: Invalid URN format or missing required parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication required or token is invalid
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '404':
          description: One or more entities not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /entities/v1/latest:
    get:
      operationId: getEntityLatestAspects
      summary: DataHub Retrieve latest entity aspects
      description: >-
        Retrieve the latest aspects for one or more entities from the DataHub
        metadata graph. Requires raw URN strings and supports fetching specific
        aspects by name. Only a single entity type may be queried per request.
      tags:
        - Entities
      parameters:
        - $ref: '#/components/parameters/Urns'
        - $ref: '#/components/parameters/AspectNames'
      responses:
        '200':
          description: Entity aspects retrieved successfully
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/EntityAspectResponse'
        '400':
          description: Invalid URN format or mixed entity types in a single request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication required or token is invalid
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '404':
          description: Entity not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /relationships/v1/:
    get:
      operationId: getRelationships
      summary: DataHub Query entity relationships
      description: >-
        Query the relationship graph to navigate connections between entities.
        Returns relationships for a given entity URN, with support for filtering
        by relationship type and traversal direction. Use this endpoint to
        discover lineage, ownership, containment, and other graph edges.
      tags:
        - Relationships
      parameters:
        - name: urn
          in: query
          required: true
          description: >-
            The URN of the target entity to query relationships for.
          schema:
            type: string
            example: urn:li:dataset:(urn:li:dataPlatform:hive,SampleHiveDataset,PROD)
        - name: relationshipTypes
          in: query
          required: false
          description: >-
            Filter results to specific relationship types such as OwnedBy,
            Contains, DownstreamOf, or Produces.
          schema:
            type: array
            items:
              type: string
        - name: direction
          in: query
          required: false
          description: >-
            Direction of relationship traversal relative to the target entity.
          schema:
            type: string
            enum:
              - INCOMING
              - OUTGOING
        - name: start
          in: query
          required: false
          description: >-
            Pagination offset for the result set.
          schema:
            type: integer
            default: 0
        - name: count
          in: query
          required: false
          description: >-
            Maximum number of relationships to return.
          schema:
            type: integer
            default: 10
      responses:
        '200':
          description: Relationships retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RelationshipsResponse'
        '400':
          description: Invalid URN format or query parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication required or token is invalid
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /timeline/:
    get:
      operationId: getTimeline
      summary: DataHub Query entity timeline
      description: >-
        Query the versioned history of an entity's aspects over time. Useful for
        tracking changes such as schema modifications, documentation updates,
        ownership transfers, and tag additions that have occurred on a given
        entity. Returns a chronological list of aspect versions with timestamps
        and audit information.
      tags:
        - Timeline
      parameters:
        - name: urn
          in: query
          required: true
          description: >-
            The URN of the entity whose timeline to retrieve.
          schema:
            type: string
            example: urn:li:dataset:(urn:li:dataPlatform:hive,SampleHiveDataset,PROD)
        - name: aspectNames
          in: query
          required: false
          description: >-
            The names of aspects to include in the timeline. If not specified,
            all aspects are returned.
          schema:
            type: array
            items:
              type: string
        - name: startTimeMillis
          in: query
          required: false
          description: >-
            Start of the time range in epoch milliseconds.
          schema:
            type: integer
            format: int64
        - name: endTimeMillis
          in: query
          required: false
          description: >-
            End of the time range in epoch milliseconds.
          schema:
            type: integer
            format: int64
      responses:
        '200':
          description: Timeline retrieved successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TimelineResponse'
        '400':
          description: Invalid URN format or query parameters
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication required or token is invalid
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '404':
          description: Entity not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /platform/entities/v1:
    post:
      operationId: emitPlatformEvents
      summary: DataHub Emit platform metadata events
      description: >-
        Write metadata events using the standard platform format. Provides an
        alternative ingestion path for emitting metadata change proposals (MCPs)
        to the DataHub metadata graph. Events are processed asynchronously and
        undergo basic schema validation upon receipt.
      tags:
        - Platform
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: array
              items:
                $ref: '#/components/schemas/MetadataChangeProposal'
      responses:
        '200':
          description: Platform events accepted for processing
        '400':
          description: Invalid event format or schema validation failure
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication required or token is invalid
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /v3/entity/{entityName}/batchGet:
    post:
      operationId: batchGetEntities
      summary: DataHub Batch fetch entities
      description: >-
        Fetch multiple entities and their aspects in a single request. Supports
        retrieving specific aspect versions using the If-Version-Match header
        for conditional reads. Allows fetching entities in bulk with fine-grained
        control over which aspects and versions are returned.
      tags:
        - Batch
      parameters:
        - name: entityName
          in: path
          required: true
          description: >-
            The type name of the entities to fetch, such as dataset, chart,
            dashboard, dataFlow, dataJob, or corpUser.
          schema:
            type: string
            example: dataset
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: array
              items:
                $ref: '#/components/schemas/BatchGetRequest'
      responses:
        '200':
          description: Entities fetched successfully
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/EntityAspectResponse'
        '400':
          description: Invalid request body or entity name
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication required or token is invalid
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: >-
        DataHub personal access token or session token. Generate tokens via
        the DataHub settings panel or programmatically using the token
        management API. Pass the token in the Authorization header as
        Bearer <token>.
  parameters:
    Urns:
      name: urns
      in: query
      required: true
      description: >-
        One or more entity URNs to operate on. Only a single entity type may
        be queried per request. URNs follow the format
        urn:li:{entityType}:{key}.
      schema:
        type: array
        items:
          type: string
        example:
          - urn:li:dataset:(urn:li:dataPlatform:hive,SampleHiveDataset,PROD)
    AspectNames:
      name: aspectNames
      in: query
      required: false
      description: >-
        Specific aspect names to retrieve for the requested entities. If not
        provided, all aspects are returned.
      schema:
        type: array
        items:
          type: string
        example:
          - datasetProperties
          - schemaMetadata
          - ownership
    SoftDelete:
      name: soft
      in: query
      required: false
      description: >-
        Whether to perform a soft delete (marking the entity as removed while
        preserving metadata) or a hard delete (permanently removing all
        metadata). Defaults to true (soft delete).
      schema:
        type: boolean
        default: true
    CreateEntityIfNotExists:
      name: createEntityIfNotExists
      in: query
      required: false
      description: >-
        When set to true, the entity will only be created if it does not
        already exist. If the entity already exists, the request is ignored.
      schema:
        type: boolean
        default: false
  schemas:
    EntityAspectRequest:
      type: object
      description: >-
        A request to upsert an entity-aspect pair in the DataHub metadata
        graph. Contains the entity URN, entity type, aspect name, and the
        aspect value to write.
      required:
        - entityUrn
        - entityType
        - aspectName
        - aspect
      properties:
        entityUrn:
          type: string
          description: >-
            The unique URN identifier for the entity being modified.
          example: urn:li:dataset:(urn:li:dataPlatform:hive,SampleHiveDataset,PROD)
        entityType:
          type: string
          description: >-
            The type of the entity being modified, such as dataset, chart,
            dashboard, dataFlow, or dataJob.
          example: dataset
        aspectName:
          type: string
          description: >-
            The name of the aspect being written, such as datasetProperties,
            schemaMetadata, ownership, or globalTags.
          example: datasetProperties
        aspect:
          type: object
          description: >-
            The aspect value to write. The structure varies depending on the
            aspect name and follows the PDL schema definitions in the DataHub
            metadata models.
    EntityAspectResponse:
      type: object
      description: >-
        A response containing an entity and its requested aspects from the
        DataHub metadata graph.
      properties:
        entityUrn:
          type: string
          description: >-
            The unique URN identifier for the entity.
          example: urn:li:dataset:(urn:li:dataPlatform:hive,SampleHiveDataset,PROD)
        entityType:
          type: string
          description: >-
            The type of the entity.
          example: dataset
        aspects:
          type: object
          description: >-
            A map of aspect names to their values for the requested entity.
          additionalProperties:
            $ref: '#/components/schemas/AspectValue'
    AspectValue:
      type: object
      description: >-
        The value of an aspect including its content and metadata.
      properties:
        value:
          type: object
          description: >-
            The aspect payload following its PDL schema definition.
        contentType:
          type: string
          description: >-
            The content type of the aspect value, typically
            application/json.
          example: application/json
        created:
          $ref: '#/components/schemas/AuditStamp'
    AuditStamp:
      type: object
      description: >-
        An audit stamp recording who made a change and when.
      properties:
        time:
          type: integer
          format: int64
          description: >-
            The timestamp of the change in epoch milliseconds.
        actor:
          type: string
          description: >-
            The URN of the actor who made the change.
          example: urn:li:corpuser:datahub
    MetadataChangeProposal:
      type: object
      description: >-
        A metadata change proposal (MCP) representing a proposed change to
        the metadata graph. MCPs are the standard format for ingesting
        metadata into DataHub and are processed asynchronously.
      required:
        - entityUrn
        - entityType
        - aspectName
        - changeType
        - aspect
      properties:
        entityUrn:
          type: string
          description: >-
            The unique URN identifier for the target entity.
          example: urn:li:dataset:(urn:li:dataPlatform:hive,SampleHiveDataset,PROD)
        entityType:
          type: string
          description: >-
            The type of the target entity.
          example: dataset
        aspectName:
          type: string
          description: >-
            The name of the aspect being changed.
          example: datasetProperties
        changeType:
          type: string
          description: >-
            The type of change being proposed.
          enum:
            - UPSERT
            - CREATE
            - DELETE
            - RESTATE
        aspect:
          type: object
          description: >-
            The new aspect value following its PDL schema definition.
        systemMetadata:
          $ref: '#/components/schemas/SystemMetadata'
    SystemMetadata:
      type: object
      description: >-
        System-level metadata associated with a metadata change, including
        ingestion run identifiers and provenance information.
      properties:
        runId:
          type: string
          description: >-
            The identifier of the ingestion run that produced this change.
        lastObserved:
          type: integer
          format: int64
          description: >-
            The timestamp when this metadata was last observed in epoch
            milliseconds.
        registryName:
          type: string
          description: >-
            The name of the model registry associated with this change.
        registryVersion:
          type: string
          description: >-
            The version of the model registry.
    RelationshipsResponse:
      type: object
      description: >-
        Response containing relationships for a queried entity.
      properties:
        start:
          type: integer
          description: >-
            The pagination offset of the result set.
        count:
          type: integer
          description: >-
            The number of relationships returned.
        total:
          type: integer
          description: >-
            The total number of matching relationships.
        relationships:
          type: array
          description: >-
            The list of relationships matching the query.
          items:
            $ref: '#/components/schemas/Relationship'
    Relationship:
      type: object
      description: >-
        A named edge connecting two entities in the metadata graph.
      properties:
        type:
          type: string
          description: >-
            The relationship type name, such as OwnedBy, Contains,
            DownstreamOf, or Produces.
          example: DownstreamOf
        entity:
          type: string
          description: >-
            The URN of the related entity.
          example: urn:li:dataset:(urn:li:dataPlatform:hive,OtherDataset,PROD)
        direction:
          type: string
          description: >-
            The traversal direction of this relationship.
          enum:
            - INCOMING
            - OUTGOING
    TimelineResponse:
      type: object
      description: >-
        Response containing the versioned history of an entity's aspects.
      properties:
        changeTransactions:
          type: array
          description: >-
            A chronological list of change transactions for the entity.
          items:
            $ref: '#/components/schemas/ChangeTransaction'
    ChangeTransaction:
      type: object
      description: >-
        A single change transaction in the entity's timeline representing
        one or more aspect modifications at a specific point in time.
      properties:
        timestamp:
          type: integer
          format: int64
          description: >-
            The timestamp of the change in epoch milliseconds.
        semVer:
          type: string
          description: >-
            The semantic version assigned to this change.
        versionStamp:
          type: string
          description: >-
            A version stamp uniquely identifying this change.
        changeEvents:
          type: array
          description: >-
            The individual change events within this transaction.
          items:
            $ref: '#/components/schemas/ChangeEvent'
    ChangeEvent:
      type: object
      description: >-
        An individual change event describing a modification to a specific
        aspect of an entity.
      properties:
        changeType:
          type: string
          description: >-
            The type of change that occurred.
          enum:
            - ADD
            - MODIFY
            - REMOVE
        semVerChange:
          type: string
          description: >-
            The semantic versioning category of this change.
          enum:
            - MAJOR
            - MINOR
            - PATCH
        description:
          type: string
          description: >-
            A human-readable description of the change.
        target:
          type: string
          description: >-
            The target element that was changed, such as a field name.
    BatchGetRequest:
      type: object
      description: >-
        A request to fetch a specific entity and its aspects in a batch
        operation.
      required:
        - urn
      properties:
        urn:
          type: string
          description: >-
            The URN of the entity to fetch.
          example: urn:li:dataset:(urn:li:dataPlatform:hive,SampleHiveDataset,PROD)
        aspectNames:
          type: array
          description: >-
            Specific aspects to retrieve. If not provided, all aspects are
            returned.
          items:
            type: string
    Error:
      type: object
      description: >-
        An error response from the DataHub API.
      properties:
        message:
          type: string
          description: >-
            A human-readable description of the error.
        status:
          type: integer
          description: >-
            The HTTP status code.
        exceptionClass:
          type: string
          description: >-
            The exception class name if applicable.