LlamaCloud Extraction API

openapi: 3.0.1
info:
  title: LlamaCloud Documents Extraction API
  description: REST API for the LlamaCloud managed document platform from LlamaIndex, covering LlamaParse document parsing, managed ingestion pipelines and indexes, document and file management, retrieval, and LlamaExtract structured extraction. All endpoints are authenticated with a Bearer API key.
  termsOfService: https://www.llamaindex.ai/terms-of-service
  contact:
    name: LlamaIndex Support
    email: support@llamaindex.ai
  version: '1.0'
servers:
- url: https://api.cloud.llamaindex.ai/api/v1
  description: LlamaCloud v1 API
security:
- bearerAuth: []
tags:
- name: Extraction
  description: LlamaExtract schema-driven structured extraction.
paths:
  /extraction/extraction-agents:
    post:
      operationId: createExtractionAgent
      tags:
      - Extraction
      summary: Create an extraction agent
      description: Defines a LlamaExtract agent bound to a JSON data schema describing the fields to extract from documents.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractionAgentCreate'
      responses:
        '200':
          description: Extraction agent created.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionAgent'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/ValidationError'
    get:
      operationId: listExtractionAgents
      tags:
      - Extraction
      summary: List extraction agents
      responses:
        '200':
          description: A list of extraction agents.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/ExtractionAgent'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /extraction/jobs:
    post:
      operationId: runExtractionJob
      tags:
      - Extraction
      summary: Run an extraction job
      description: Runs an extraction agent against an uploaded file and returns an async job id. Poll the job to retrieve the structured result.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractionJobCreate'
      responses:
        '200':
          description: Extraction job created.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionJob'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '422':
          $ref: '#/components/responses/ValidationError'
  /extraction/jobs/{job_id}:
    get:
      operationId: getExtractionJob
      tags:
      - Extraction
      summary: Get extraction job status
      parameters:
      - $ref: '#/components/parameters/JobId'
      responses:
        '200':
          description: Extraction job status.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionJob'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
  /extraction/jobs/{job_id}/result:
    get:
      operationId: getExtractionJobResult
      tags:
      - Extraction
      summary: Get extraction job result
      parameters:
      - $ref: '#/components/parameters/JobId'
      responses:
        '200':
          description: Structured extraction result.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionResult'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
components:
  schemas:
    ExtractionAgentCreate:
      type: object
      required:
      - name
      - data_schema
      properties:
        name:
          type: string
        data_schema:
          type: object
          additionalProperties: true
        config:
          type: object
          additionalProperties: true
    ExtractionAgent:
      type: object
      properties:
        id:
          type: string
        name:
          type: string
        data_schema:
          type: object
          additionalProperties: true
        project_id:
          type: string
        created_at:
          type: string
          format: date-time
    ExtractionResult:
      type: object
      properties:
        data:
          type: object
          additionalProperties: true
        extraction_metadata:
          type: object
          additionalProperties: true
    Error:
      type: object
      properties:
        detail:
          type: string
    ExtractionJobCreate:
      type: object
      required:
      - extraction_agent_id
      - file_id
      properties:
        extraction_agent_id:
          type: string
        file_id:
          type: string
    ExtractionJob:
      type: object
      properties:
        id:
          type: string
        extraction_agent_id:
          type: string
        status:
          type: string
          enum:
          - PENDING
          - RUNNING
          - SUCCESS
          - ERROR
          - CANCELLED
        error_message:
          type: string
          nullable: true
  responses:
    NotFound:
      description: Resource not found.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    ValidationError:
      description: Request validation failed.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  parameters:
    JobId:
      name: job_id
      in: path
      required: true
      schema:
        type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: LlamaCloud API key sent as a Bearer token.