Marqo

Marqo Recommendations API

Return documents similar to one or more reference documents.

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/marqo-recommendations-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: 3.1.0
info:
  title: Marqo REST Documents Recommendations API
  version: '2.26'
  summary: Open-source multimodal vector search engine REST API.
  description: 'Marqo is an open-source vector search engine that bundles index storage

    (Vespa) and embedding inference (Sentence Transformers, OpenCLIP, ONNX)

    behind a single FastAPI HTTP surface. The engine is reachable at

    `http://{host}:8882` by default and publishes its live OpenAPI schema at

    `/openapi.json` with interactive Swagger UI at `/docs`. The same surface

    is exposed by the hosted Marqo Cloud product at `https://api.marqo.ai`

    with bearer-token authentication.


    This profile is a hand-curated, best-effort companion spec covering the

    most-used operations across indexes, documents, search, embeddings,

    models, and telemetry. For the canonical, version-pinned specification

    of a deployment, fetch `/openapi.json` directly from the running engine.

    '
  contact:
    name: Marqo
    url: https://www.marqo.ai
  license:
    name: Apache 2.0
    url: https://github.com/marqo-ai/marqo/blob/mainline/LICENSE
servers:
- url: http://localhost:8882
  description: Default Marqo open-source engine endpoint
- url: https://api.marqo.ai
  description: Marqo Cloud endpoint (bearer authentication)
security: []
tags:
- name: Recommendations
  description: Return documents similar to one or more reference documents.
paths:
  /indexes/{index_name}/recommend:
    post:
      tags:
      - Recommendations
      summary: Recommend Similar Documents
      operationId: recommend
      parameters:
      - $ref: '#/components/parameters/IndexName'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - documents
              properties:
                documents:
                  type: array
                  items:
                    type: string
                  description: IDs of seed documents.
                limit:
                  type: integer
                  minimum: 1
                  default: 10
      responses:
        '200':
          description: Recommended documents.
components:
  parameters:
    IndexName:
      in: path
      name: index_name
      required: true
      schema:
        type: string
      description: Name of the Marqo index.
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: 'Marqo Cloud API key passed as `Authorization: Bearer {api_key}`.

        The open-source engine accepts unauthenticated requests by default.

        '