Vectorize

Vectorize Extraction API

Vectorize Iris document extraction.

Documentation GitHub OpenAPI

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this

find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/vectorize-io-extraction-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.0.1
info:
  title: Vectorize AI Platform Connectors Extraction API
  description: 'The Vectorize API lets developers programmatically build and operate RAG (retrieval-augmented generation) pipelines: create / start / stop / delete pipelines, run retrieval against a pipeline''s vector index, manage source, destination, and AI-platform connectors, upload files, extract documents with Iris, and run deep research. All paths are organization-scoped under /org/{organizationId}. Authentication uses a Bearer access token.'
  termsOfService: https://vectorize.io/terms
  contact:
    name: Vectorize Support
    url: https://vectorize.io
  version: 0.1.2
servers:
- url: https://api.vectorize.io/v1
  description: Vectorize API
security:
- bearerAuth: []
tags:
- name: Extraction
  description: Vectorize Iris document extraction.
paths:
  /org/{organizationId}/extraction:
    post:
      operationId: startExtraction
      tags:
      - Extraction
      summary: Start content extraction from a file
      description: Starts a Vectorize Iris extraction job against a previously uploaded file, converting it into Markdown chunks with optional metadata extraction.
      parameters:
      - $ref: '#/components/parameters/OrganizationId'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/StartExtractionRequest'
      responses:
        '200':
          description: Extraction started.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StartExtractionResponse'
        '400':
          $ref: '#/components/responses/Error'
  /org/{organizationId}/extraction/{extractionId}:
    get:
      operationId: getExtractionResult
      tags:
      - Extraction
      summary: Get extraction result
      parameters:
      - $ref: '#/components/parameters/OrganizationId'
      - name: extractionId
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Extraction result. Poll until ready is true.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionResultResponse'
        '404':
          $ref: '#/components/responses/Error'
components:
  schemas:
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
        details:
          type: string
        failedUpdates:
          type: array
          items:
            type: string
        successfulUpdates:
          type: array
          items:
            type: string
      required:
      - error
    ExtractionResultResponse:
      type: object
      properties:
        ready:
          type: boolean
        data:
          $ref: '#/components/schemas/ExtractionResult'
      required:
      - ready
    StartExtractionResponse:
      type: object
      properties:
        message:
          type: string
        extractionId:
          type: string
      required:
      - message
      - extractionId
    StartExtractionRequest:
      type: object
      properties:
        fileId:
          type: string
        type:
          type: string
          enum:
          - iris
          default: iris
        chunkingStrategy:
          type: string
          enum:
          - markdown
          default: markdown
        chunkSize:
          type: number
          default: 256
        metadata:
          type: object
          description: Metadata extraction strategy.
          additionalProperties: true
      required:
      - fileId
    ExtractionResult:
      type: object
      properties:
        success:
          type: boolean
        chunks:
          type: array
          items:
            type: string
        text:
          type: string
        metadata:
          type: string
        metadataSchema:
          type: string
        chunksMetadata:
          type: array
          items:
            type: string
        chunksSchema:
          type: array
          items:
            type: string
        error:
          type: string
      required:
      - success
  parameters:
    OrganizationId:
      name: organizationId
      in: path
      required: true
      description: Vectorize organization identifier.
      schema:
        type: string
  responses:
    Error:
      description: Error response.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Vectorize API access token passed as a Bearer token.