LlamaParse Split API

openapi: 3.2.0
info:
  title: Llama Platform Agent Data Split API
  version: 0.1.0
servers:
- url: https://api.cloud.llamaindex.ai
  description: Base URL declared by the provider in apis.yml (roadmap#122).
tags:
- name: Split
paths:
  /api/v1/beta/split/jobs:
    post:
      tags:
      - Split
      summary: Create Split Job
      description: Create a document split job.
      operationId: create_split_job_api_v1_beta_split_jobs_post
      security:
      - HTTPBearer: []
      parameters:
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SplitCreateRequest'
      responses:
        '201':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SplitJobResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    get:
      tags:
      - Split
      summary: List Split Jobs
      description: List document split jobs.
      operationId: list_split_jobs_api_v1_beta_split_jobs_get
      security:
      - HTTPBearer: []
      parameters:
      - name: status
        in: query
        required: false
        schema:
          anyOf:
          - enum:
            - pending
            - processing
            - completed
            - failed
            - cancelled
            type: string
          - type: 'null'
          description: Filter by job status (pending, processing, completed, failed, cancelled)
          title: Status
        description: Filter by job status (pending, processing, completed, failed, cancelled)
      - name: job_ids
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              type: string
          - type: 'null'
          description: Filter by specific job IDs
          title: Job Ids
        description: Filter by specific job IDs
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: page_size
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
          - type: 'null'
          title: Page Size
      - name: page_token
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Page Token
      - name: created_at_on_or_after
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: Include items created at or after this timestamp (inclusive)
          title: Created At On Or After
        description: Include items created at or after this timestamp (inclusive)
      - name: created_at_on_or_before
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          description: Include items created at or before this timestamp (inclusive)
          title: Created At On Or Before
        description: Include items created at or before this timestamp (inclusive)
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SplitJobQueryResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/beta/split/jobs/{split_job_id}:
    get:
      tags:
      - Split
      summary: Get Split Job
      description: Get a document split job.
      operationId: get_split_job_api_v1_beta_split_jobs__split_job_id__get
      security:
      - HTTPBearer: []
      parameters:
      - name: split_job_id
        in: path
        required: true
        schema:
          type: string
          title: Split Job Id
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SplitJobResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    SplitDocumentInput:
      properties:
        type:
          type: string
          title: Type
          description: 'Type of document input. Valid values are: file_id'
        value:
          type: string
          title: Value
          description: Document identifier.
      type: object
      required:
      - type
      - value
      title: SplitDocumentInput
      description: Document input specification for beta API.
    SplitJobResponse:
      properties:
        id:
          type: string
          title: Id
          description: Unique identifier for the split job.
        created_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Created At
          description: Creation datetime
        updated_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Updated At
          description: Update datetime
        project_id:
          type: string
          title: Project Id
          description: Project ID this job belongs to.
        user_id:
          type: string
          title: User Id
          description: User ID who created this job.
        configuration_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Configuration Id
          description: Split configuration ID used for this job.
        document_input:
          $ref: '#/components/schemas/SplitDocumentInput'
          description: Document that was split.
        categories:
          items:
            $ref: '#/components/schemas/SplitCategory'
          type: array
          title: Categories
          description: Categories used for splitting.
        status:
          type: string
          title: Status
          description: 'Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.'
        result:
          anyOf:
          - $ref: '#/components/schemas/SplitResultResponse'
          - type: 'null'
          description: Split result (available when status is COMPLETED).
        error_message:
          anyOf:
          - type: string
          - type: 'null'
          title: Error Message
          description: Error message if the job failed.
      type: object
      required:
      - id
      - project_id
      - user_id
      - document_input
      - categories
      - status
      title: SplitJobResponse
      description: Beta response — uses nested document_input object.
    SplitCategory:
      properties:
        name:
          type: string
          maxLength: 200
          minLength: 1
          title: Name
          description: Name of the category.
        description:
          anyOf:
          - type: string
            maxLength: 2000
            minLength: 1
          - type: 'null'
          title: Description
          description: Optional description of what content belongs in this category.
      type: object
      required:
      - name
      title: SplitCategory
      description: Category definition for document splitting.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    SplitCreateRequest:
      properties:
        document_input:
          $ref: '#/components/schemas/SplitDocumentInput'
          description: Document to be split.
        configuration:
          anyOf:
          - $ref: '#/components/schemas/SplitConfiguration'
          - type: 'null'
          description: Inline split configuration.
        configuration_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Configuration Id
          description: Saved split configuration ID.
      type: object
      required:
      - document_input
      title: SplitCreateRequest
      description: Beta create request — accepts legacy document_input and flat formats.
    SplitConfiguration:
      properties:
        categories:
          items:
            $ref: '#/components/schemas/SplitCategory'
          type: array
          maxItems: 50
          minItems: 1
          title: Categories
          description: Categories to split documents into.
        splitting_strategy:
          $ref: '#/components/schemas/SplitStrategy'
          description: Strategy for splitting documents.
      type: object
      required:
      - categories
      title: SplitConfiguration
      description: Split configuration with categories and splitting strategy.
    SplitJobQueryResponse:
      properties:
        items:
          items:
            $ref: '#/components/schemas/SplitJobResponse'
          type: array
          title: Items
          description: The list of items.
        next_page_token:
          anyOf:
          - type: string
          - type: 'null'
          title: Next Page Token
          description: A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.
        total_size:
          anyOf:
          - type: integer
          - type: 'null'
          title: Total Size
          description: The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only.
      type: object
      required:
      - items
      title: SplitJobQueryResponse
      description: Beta paginated list of split jobs.
    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
    SplitSegmentResponse:
      properties:
        category:
          type: string
          title: Category
          description: Category name this split belongs to.
        pages:
          items:
            type: integer
          type: array
          title: Pages
          description: 1-indexed page numbers in this split.
        confidence_category:
          type: string
          title: Confidence Category
          description: 'Categorical confidence level. Valid values are: high, medium, low.'
      type: object
      required:
      - category
      - pages
      - confidence_category
      title: SplitSegmentResponse
      description: A segment of the split document.
    SplitResultResponse:
      properties:
        segments:
          items:
            $ref: '#/components/schemas/SplitSegmentResponse'
          type: array
          title: Segments
          description: List of document segments.
      type: object
      required:
      - segments
      title: SplitResultResponse
      description: Result of a completed split job.
    SplitStrategy:
      properties:
        allow_uncategorized:
          type: string
          enum:
          - include
          - forbid
          - omit
          title: Allow Uncategorized
          description: 'Controls handling of pages that don''t match any category. ''include'': pages can be grouped as ''uncategorized'' and included in results. ''forbid'': all pages must be assigned to a defined category. ''omit'': pages can be classified as ''uncategorized'' but are excluded from results.'
          default: include
      type: object
      title: SplitStrategy
      description: Configuration for how to split the document.
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer