llamaindex Jobs API

openapi: 3.1.0
info:
  title: LlamaIndex LlamaCloud Data Sources Jobs API
  description: The LlamaCloud API is the central REST API for LlamaIndex's cloud platform, providing programmatic access to managed document processing, indexing, and retrieval services. It enables developers to build production-grade LLM applications by leveraging cloud-hosted infrastructure for document ingestion, knowledge management, and agent orchestration. The API supports authentication via API keys and is available in both US and EU regions.
  version: '1.0'
  contact:
    name: LlamaIndex Support
    url: https://www.llamaindex.ai/contact
  termsOfService: https://www.llamaindex.ai/terms-of-service
servers:
- url: https://api.cloud.llamaindex.ai/api/v1
  description: US Production Server
- url: https://api.cloud.llamaindex.eu/api/v1
  description: EU Production Server
security:
- bearerAuth: []
tags:
- name: Jobs
  description: Monitor and retrieve results from asynchronous parsing jobs.
paths:
  /parse/jobs:
    get:
      operationId: listParseJobs
      summary: List parse jobs
      description: Retrieve a list of parse jobs for the authenticated project. Supports optional filtering and pagination to narrow down results.
      tags:
      - Jobs
      parameters:
      - name: project_id
        in: query
        description: Filter jobs by project identifier.
        required: false
        schema:
          type: string
      - name: limit
        in: query
        description: Maximum number of jobs to return.
        required: false
        schema:
          type: integer
          minimum: 1
      - name: offset
        in: query
        description: Number of jobs to skip for pagination.
        required: false
        schema:
          type: integer
          minimum: 0
      responses:
        '200':
          description: Successfully retrieved list of parse jobs
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/ParseJob'
        '401':
          description: Unauthorized - invalid or missing API key
  /parse/jobs/{jobId}:
    get:
      operationId: getParseJob
      summary: Get parse job status
      description: Retrieve the status and optionally the results of a parse job. Use the expand parameter to control what parsed content is returned, including text, markdown, structured JSON, or metadata. Poll this endpoint to check job completion status.
      tags:
      - Jobs
      parameters:
      - $ref: '#/components/parameters/jobId'
      - name: expand
        in: query
        description: Comma-separated list of result fields to include in the response. Controls whether text, markdown, structured JSON, or metadata is returned with the job status.
        required: false
        schema:
          type: string
      responses:
        '200':
          description: Successfully retrieved parse job status and results
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ParseJob'
        '401':
          description: Unauthorized - invalid or missing API key
        '404':
          description: Parse job not found
  /parse/jobs/{jobId}/result:
    get:
      operationId: getParseJobResult
      summary: Get parse job result
      description: Retrieve the full parsed result of a completed parse job. Returns the extracted content in the requested format. The job must be in a completed state for results to be available.
      tags:
      - Jobs
      parameters:
      - $ref: '#/components/parameters/jobId'
      responses:
        '200':
          description: Successfully retrieved parse job result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ParseResult'
        '401':
          description: Unauthorized - invalid or missing API key
        '404':
          description: Parse job not found or not completed
components:
  parameters:
    jobId:
      name: jobId
      in: path
      description: Unique identifier of the parse job.
      required: true
      schema:
        type: string
  schemas:
    ParseResult:
      type: object
      description: The parsed output of a document, containing extracted content in various formats.
      properties:
        text:
          type: string
          description: Plain text representation of the parsed content.
        markdown:
          type: string
          description: Markdown-formatted representation of the parsed content.
        json:
          type: object
          additionalProperties: true
          description: Structured JSON representation of the parsed content.
        pages:
          type: array
          description: Per-page parsing results.
          items:
            $ref: '#/components/schemas/ParsePage'
        metadata:
          type: object
          additionalProperties: true
          description: Metadata extracted from the document.
    ParsePage:
      type: object
      description: Parsed content for a single page of a document.
      properties:
        page_number:
          type: integer
          minimum: 1
          description: 1-based page number.
        text:
          type: string
          description: Plain text content of the page.
        markdown:
          type: string
          description: Markdown-formatted content of the page.
    ParseJob:
      type: object
      description: A parse job representing the asynchronous processing of a document.
      properties:
        id:
          type: string
          description: Unique identifier of the parse job.
        status:
          type: string
          enum:
          - pending
          - processing
          - completed
          - failed
          description: Current status of the parse job.
        tier:
          type: string
          enum:
          - fast
          - cost_effective
          - agentic
          - agentic_plus
          description: Parsing tier used for this job.
        file_name:
          type: string
          description: Name of the parsed file.
        num_pages:
          type: integer
          description: Total number of pages in the document.
        created_at:
          type: string
          format: date-time
          description: Timestamp when the parse job was created.
        completed_at:
          type: string
          format: date-time
          description: Timestamp when the parse job completed, if applicable.
        result:
          $ref: '#/components/schemas/ParseResult'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: LlamaCloud API key obtained from the LlamaCloud dashboard. Include as a Bearer token in the Authorization header.
externalDocs:
  description: LlamaCloud API Documentation
  url: https://developers.api.llamaindex.ai/