llamaindex Extraction Jobs API

openapi: 3.2.0
info:
  title: LlamaIndex LlamaCloud Data Sources Extraction 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: Extraction Jobs
  description: Run and monitor asynchronous extraction jobs that process documents through extraction agents.
paths:
  /extraction/jobs:
    post:
      operationId: createExtractionJob
      summary: Create an extraction job
      description: Run an extraction job by specifying an extraction agent and one or more files to process. The job runs asynchronously and can be polled for status and results.
      tags:
      - Extraction Jobs
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateExtractionJobRequest'
      responses:
        '200':
          description: Extraction job created successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionJob'
        '400':
          description: Bad request - invalid job parameters
        '401':
          description: Unauthorized - invalid or missing API key
  /extraction/jobs/{jobId}:
    get:
      operationId: getExtractionJob
      summary: Get extraction job status
      description: Retrieve the current status of an extraction job. Poll this endpoint to check whether the job has completed processing.
      tags:
      - Extraction Jobs
      parameters:
      - $ref: '#/components/parameters/jobId'
      responses:
        '200':
          description: Successfully retrieved extraction job status
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionJob'
        '401':
          description: Unauthorized - invalid or missing API key
        '404':
          description: Extraction job not found
  /extraction/jobs/{jobId}/result:
    get:
      operationId: getExtractionJobResult
      summary: Get extraction job result
      description: Retrieve the structured data extracted from the documents processed by a completed extraction job. Results conform to the schema defined in the extraction agent.
      tags:
      - Extraction Jobs
      parameters:
      - $ref: '#/components/parameters/jobId'
      responses:
        '200':
          description: Successfully retrieved extraction results
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionResult'
        '401':
          description: Unauthorized - invalid or missing API key
        '404':
          description: Extraction job not found or not completed
components:
  parameters:
    jobId:
      name: jobId
      in: path
      description: Unique identifier of the extraction job.
      required: true
      schema:
        type: string
  schemas:
    FileExtractionResult:
      type: object
      description: Extraction result for a single file.
      properties:
        file_id:
          type: string
          description: Identifier of the processed file.
        file_name:
          type: string
          description: Name of the processed file.
        data:
          type: object
          additionalProperties: true
          description: Structured data extracted from the file, conforming to the extraction agent schema.
        status:
          type: string
          enum:
          - success
          - error
          description: Status of the extraction for this specific file.
        error:
          type: string
          description: Error message if extraction failed for this file.
    CreateExtractionJobRequest:
      type: object
      description: Request body for creating an extraction job.
      required:
      - extraction_agent_id
      - file_ids
      properties:
        extraction_agent_id:
          type: string
          description: Identifier of the extraction agent to use for processing.
        file_ids:
          type: array
          items:
            type: string
          description: List of file identifiers to process in this extraction job.
    ExtractionResult:
      type: object
      description: Structured data extracted from documents by a completed extraction job.
      properties:
        job_id:
          type: string
          description: Identifier of the extraction job that produced this result.
        results:
          type: array
          description: List of extraction results, one per processed file.
          items:
            $ref: '#/components/schemas/FileExtractionResult'
    ExtractionJob:
      type: object
      description: An asynchronous extraction job that processes documents through an extraction agent.
      properties:
        id:
          type: string
          description: Unique identifier of the extraction job.
        extraction_agent_id:
          type: string
          description: Identifier of the extraction agent used for this job.
        status:
          type: string
          enum:
          - pending
          - processing
          - completed
          - failed
          description: Current status of the extraction job.
        file_ids:
          type: array
          items:
            type: string
          description: Identifiers of the files being processed.
        created_at:
          type: string
          format: date-time
          description: Timestamp when the extraction job was created.
        completed_at:
          type: string
          format: date-time
          description: Timestamp when the extraction job completed, if applicable.
  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/