openapi: 3.0.3
info:
  title: Arize-Phoenix REST annotation_configs datasets API
  description: Schema for Arize-Phoenix REST API
  version: '1.0'
tags:
- name: datasets
paths:
  /v1/datasets:
    get:
      tags:
      - datasets
      summary: List datasets
      operationId: listDatasets
      parameters:
      - name: cursor
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: Cursor for pagination
          title: Cursor
        description: Cursor for pagination
      - name: name
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: An optional dataset name to filter by
          title: Name
        description: An optional dataset name to filter by
      - name: limit
        in: query
        required: false
        schema:
          type: integer
          exclusiveMinimum: 0
          description: The max number of datasets to return at a time.
          default: 10
          title: Limit
        description: The max number of datasets to return at a time.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListDatasetsResponseBody'
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Unprocessable Entity
  /v1/datasets/{id}:
    delete:
      tags:
      - datasets
      summary: Delete dataset by ID
      operationId: deleteDatasetById
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset to delete.
          title: Id
        description: The ID of the dataset to delete.
      responses:
        '204':
          description: Successful Response
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '404':
          content:
            text/plain:
              schema:
                type: string
          description: Dataset not found
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Invalid dataset ID
    get:
      tags:
      - datasets
      summary: Get dataset by ID
      operationId: getDataset
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset
          title: Id
        description: The ID of the dataset
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetDatasetResponseBody'
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '404':
          content:
            text/plain:
              schema:
                type: string
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/datasets/{id}/versions:
    get:
      tags:
      - datasets
      summary: List dataset versions
      operationId: listDatasetVersionsByDatasetId
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset
          title: Id
        description: The ID of the dataset
      - name: cursor
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: Cursor for pagination
          title: Cursor
        description: Cursor for pagination
      - name: limit
        in: query
        required: false
        schema:
          type: integer
          exclusiveMinimum: 0
          description: The max number of dataset versions to return at a time
          default: 10
          title: Limit
        description: The max number of dataset versions to return at a time
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListDatasetVersionsResponseBody'
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Unprocessable Entity
  /v1/datasets/upload:
    post:
      tags:
      - datasets
      summary: Upload dataset from JSON, JSONL, CSV, or PyArrow
      operationId: uploadDataset
      parameters:
      - name: sync
        in: query
        required: false
        schema:
          type: boolean
          description: If true, fulfill request synchronously and return JSON containing dataset_id.
          default: false
          title: Sync
        description: If true, fulfill request synchronously and return JSON containing dataset_id.
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UploadDatasetResponseBody'
                nullable: true
                title: Response Uploaddataset
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '409':
          content:
            text/plain:
              schema:
                type: string
          description: Dataset with the given name already exists (action=create).
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Invalid request body
      requestBody:
        content:
          application/json:
            schema:
              type: object
              required:
              - name
              - inputs
              properties:
                action:
                  type: string
                  enum:
                  - create
                  - append
                  - update
                name:
                  type: string
                description:
                  type: string
                inputs:
                  type: array
                  items:
                    type: object
                outputs:
                  type: array
                  items:
                    type: object
                metadata:
                  type: array
                  items:
                    type: object
                splits:
                  type: array
                  items:
                    oneOf:
                    - type: string
                    - type: array
                      items:
                        type: string
                    - type: 'null'
                  description: 'Split per example: string, string array, or null'
                span_ids:
                  type: array
                  items:
                    oneOf:
                    - type: string
                    - type: 'null'
                  description: Span IDs to link examples back to spans
                example_ids:
                  type: array
                  items:
                    oneOf:
                    - type: string
                    - type: 'null'
                  description: Optional example ID per example. If provided, it is used as the example's stable public ID.
          multipart/form-data:
            schema:
              type: object
              required:
              - name
              - input_keys[]
              - output_keys[]
              - file
              properties:
                action:
                  type: string
                  enum:
                  - create
                  - append
                  - update
                name:
                  type: string
                description:
                  type: string
                input_keys[]:
                  type: array
                  items:
                    type: string
                  uniqueItems: true
                output_keys[]:
                  type: array
                  items:
                    type: string
                  uniqueItems: true
                metadata_keys[]:
                  type: array
                  items:
                    type: string
                  uniqueItems: true
                split_keys[]:
                  type: array
                  items:
                    type: string
                  uniqueItems: true
                  description: 'Deprecated: use split_key instead. Column names for auto-assigning examples to splits'
                split_key:
                  type: string
                  description: Single column name containing split names (plain string or JSON list) per row
                flatten_keys[]:
                  type: array
                  items:
                    type: string
                  uniqueItems: true
                  description: Column names whose object values should be flattened into their selected bucket
                span_id_key:
                  type: string
                  description: Column name for span IDs to link examples back to spans
                example_id_key:
                  type: string
                  description: Column name containing stable IDs for examples. When provided, examples with matching IDs are updated in place when their content changes.
                file:
                  type: string
                  format: binary
  /v1/datasets/{id}/examples:
    get:
      tags:
      - datasets
      summary: Get examples from a dataset
      operationId: getDatasetExamples
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset
          title: Id
        description: The ID of the dataset
      - name: version_id
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: The ID of the dataset version (if omitted, returns data from the latest version)
          title: Version Id
        description: The ID of the dataset version (if omitted, returns data from the latest version)
      - name: split
        in: query
        required: false
        schema:
          type: array
          items:
            type: string
          nullable: true
          description: List of dataset split identifiers (GlobalIDs or names) to filter by
          title: Split
        description: List of dataset split identifiers (GlobalIDs or names) to filter by
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListDatasetExamplesResponseBody'
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '404':
          content:
            text/plain:
              schema:
                type: string
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /v1/datasets/{id}/csv:
    get:
      tags:
      - datasets
      summary: Download dataset examples as CSV file
      operationId: getDatasetCsv
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset
          title: Id
        description: The ID of the dataset
      - name: version_id
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: The ID of the dataset version (if omitted, returns data from the latest version)
          title: Version Id
        description: The ID of the dataset version (if omitted, returns data from the latest version)
      responses:
        '200':
          description: Successful Response
          content:
            text/csv:
              schema:
                type: string
                contentMediaType: text/csv
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Unprocessable Entity
  /v1/datasets/{id}/jsonl:
    get:
      tags:
      - datasets
      summary: Download dataset examples as JSONL file
      operationId: getDatasetJSONL
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset
          title: Id
        description: The ID of the dataset
      - name: version_id
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: The ID of the dataset version (if omitted, returns data from the latest version)
          title: Version Id
        description: The ID of the dataset version (if omitted, returns data from the latest version)
      responses:
        '200':
          description: Successful Response
          content:
            text/plain:
              schema:
                type: string
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Invalid dataset or version ID
  /v1/datasets/{id}/jsonl/openai_ft:
    get:
      tags:
      - datasets
      summary: Download dataset examples as OpenAI fine-tuning JSONL file
      operationId: getDatasetJSONLOpenAIFineTuning
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset
          title: Id
        description: The ID of the dataset
      - name: version_id
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: The ID of the dataset version (if omitted, returns data from the latest version)
          title: Version Id
        description: The ID of the dataset version (if omitted, returns data from the latest version)
      responses:
        '200':
          description: Successful Response
          content:
            text/plain:
              schema:
                type: string
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Invalid dataset or version ID
  /v1/datasets/{id}/jsonl/openai_evals:
    get:
      tags:
      - datasets
      summary: Download dataset examples as OpenAI evals JSONL file
      operationId: getDatasetJSONLOpenAIEvals
      parameters:
      - name: id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the dataset
          title: Id
        description: The ID of the dataset
      - name: version_id
        in: query
        required: false
        schema:
          type: string
          nullable: true
          description: The ID of the dataset version (if omitted, returns data from the latest version)
          title: Version Id
        description: The ID of the dataset version (if omitted, returns data from the latest version)
      responses:
        '200':
          description: Successful Response
          content:
            text/plain:
              schema:
                type: string
        '403':
          content:
            text/plain:
              schema:
                type: string
          description: Forbidden
        '422':
          content:
            text/plain:
              schema:
                type: string
          description: Invalid dataset or version ID
components:
  schemas:
    ListDatasetExamplesResponseBody:
      properties:
        data:
          $ref: '#/components/schemas/ListDatasetExamplesData'
      type: object
      required:
      - data
      title: ListDatasetExamplesResponseBody
    GetDatasetResponseBody:
      properties:
        data:
          $ref: '#/components/schemas/DatasetWithExampleCount'
      type: object
      required:
      - data
      title: GetDatasetResponseBody
    UploadDatasetResponseBody:
      properties:
        data:
          $ref: '#/components/schemas/UploadDatasetData'
      type: object
      required:
      - data
      title: UploadDatasetResponseBody
    ListDatasetExamplesData:
      properties:
        dataset_id:
          type: string
          title: Dataset Id
        version_id:
          type: string
          title: Version Id
        filtered_splits:
          items:
            type: string
          type: array
          title: Filtered Splits
        examples:
          items:
            $ref: '#/components/schemas/DatasetExample'
          type: array
          title: Examples
      type: object
      required:
      - dataset_id
      - version_id
      - examples
      title: ListDatasetExamplesData
    DatasetWithExampleCount:
      properties:
        id:
          type: string
          title: Id
        name:
          type: string
          title: Name
        description:
          type: string
          nullable: true
          title: Description
        metadata:
          additionalProperties: true
          type: object
          title: Metadata
        created_at:
          type: string
          format: date-time
          title: Created At
        updated_at:
          type: string
          format: date-time
          title: Updated At
        example_count:
          type: integer
          title: Example Count
      type: object
      required:
      - id
      - name
      - description
      - metadata
      - created_at
      - updated_at
      - example_count
      title: DatasetWithExampleCount
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    Dataset:
      properties:
        id:
          type: string
          title: Id
        name:
          type: string
          title: Name
        description:
          type: string
          nullable: true
          title: Description
        metadata:
          additionalProperties: true
          type: object
          title: Metadata
        created_at:
          type: string
          format: date-time
          title: Created At
        updated_at:
          type: string
          format: date-time
          title: Updated At
        example_count:
          type: integer
          title: Example Count
      type: object
      required:
      - id
      - name
      - description
      - metadata
      - created_at
      - updated_at
      - example_count
      title: Dataset
    UploadDatasetData:
      properties:
        dataset_id:
          type: string
          title: Dataset Id
        version_id:
          type: string
          title: Version Id
        num_created_examples:
          type: integer
          title: Num Created Examples
        num_updated_examples:
          type: integer
          title: Num Updated Examples
        num_deleted_examples:
          type: integer
          title: Num Deleted Examples
      type: object
      required:
      - dataset_id
      - version_id
      - num_created_examples
      - num_updated_examples
      - num_deleted_examples
      title: UploadDatasetData
    ListDatasetsResponseBody:
      properties:
        data:
          items:
            $ref: '#/components/schemas/Dataset'
          type: array
          title: Data
        next_cursor:
          type: string
          nullable: true
          title: Next Cursor
      type: object
      required:
      - data
      - next_cursor
      title: ListDatasetsResponseBody
    ListDatasetVersionsResponseBody:
      properties:
        data:
          items:
            $ref: '#/components/schemas/DatasetVersion'
          type: array
          title: Data
        next_cursor:
          type: string
          nullable: true
          title: Next Cursor
      type: object
      required:
      - data
      - next_cursor
      title: ListDatasetVersionsResponseBody
    DatasetExample:
      properties:
        id:
          type: string
          title: Id
        node_id:
          type: string
          title: Node Id
        input:
          additionalProperties: true
          type: object
          title: Input
        output:
          additionalProperties: true
          type: object
          title: Output
        metadata:
          additionalProperties: true
          type: object
          title: Metadata
        updated_at:
          type: string
          format: date-time
          title: Updated At
      type: object
      required:
      - id
      - node_id
      - input
      - output
      - metadata
      - updated_at
      title: DatasetExample
    DatasetVersion:
      properties:
        version_id:
          type: string
          title: Version Id
        description:
          type: string
          nullable: true
          title: Description
        metadata:
          additionalProperties: true
          type: object
          title: Metadata
        created_at:
          type: string
          format: date-time
          title: Created At
      type: object
      required:
      - version_id
      - description
      - metadata
      - created_at
      title: DatasetVersion