Algolia Recommend API

Returns related-products, frequently-bought-together, trending and look-alike recommendations trained from Insights events and catalog data, plus the Recommend rules that override them.

Operations 11

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

GET /{path} Send a custom GET request to the Recommend API · Send requests to the Algolia REST API #
Ask an LLM
“Can I call a Recommend API endpoint the client library doesn't wrap yet with a raw GET?”
“Is there a generic way to read from an arbitrary Recommend API path?”
Tell an agent
Send a raw GET request to the Recommend API path {path}.
Call GET on Recommend endpoint {path} with query parameters {parameters}.
POST /{path} Send a custom POST request to the Recommend API · Send requests to the Algolia REST API #
Ask an LLM
“What's the way to POST to a new Recommend API endpoint before the SDK supports it?”
“Can I make a raw POST call to any Recommend path?”
Tell an agent
Send a raw POST request to the Recommend API path {path}.
POST to Recommend endpoint {path} passing query parameters {parameters}.
PUT /{path} Send a custom PUT request to the Recommend API · Send requests to the Algolia REST API #
Ask an LLM
“How can I send a PUT to a Recommend API path that has no dedicated method?”
“Can I replace something at a custom Recommend endpoint using a raw PUT call?”
Tell an agent
Send a raw PUT request to the Recommend API path {path}.
Issue a PUT to Recommend endpoint {path} with query parameters {parameters}.
DELETE /{path} Send a custom DELETE request to the Recommend API · Send requests to the Algolia REST API #
Ask an LLM
“How do I send a raw DELETE to a Recommend API path the client doesn't cover?”
“Can I call DELETE on an arbitrary Recommend endpoint?”
Tell an agent destructive · confirm first
Send a raw DELETE request to the Recommend API path {path}.
Issue a DELETE against Recommend endpoint {path} with query parameters {parameters}.
POST /1/indexes/*/recommendations Get product recommendations from AI models · Retrieve recommendations #
Ask an LLM
“How do I get 'frequently bought together' or related-product recommendations for an item?”
“Can I request recommendations from several models in a single call?”
Tell an agent
Fetch recommendations for these model requests: {requests}.
Get related products and trending items using the recommendation requests {requests}.
GET /1/indexes/{indexName}/{model}/recommend/rules/{objectID} Retrieve a Recommend rule · Retrieve a rule #
Ask an LLM
“How can I look up one Recommend rule I set up in the dashboard?”
“What does a specific rule on my recommendation scenario contain?”
Tell an agent
Get Recommend rule {objectID} for model {model} on index {indexName}.
Show me the details of recommendation rule {objectID} in {indexName}'s {model} scenario.
DELETE /1/indexes/{indexName}/{model}/recommend/rules/{objectID} Delete a Recommend rule · Delete a rule #
Ask an LLM
“How do I remove a rule from a recommendation scenario?”
“Is deleting a Recommend rule immediate or does it run as a task?”
Tell an agent destructive · confirm first
Delete Recommend rule {objectID} from model {model} on index {indexName}.
Remove recommendation rule {objectID} from the {model} scenario of {indexName}.
GET /1/indexes/{indexName}/{model}/task/{taskID} Check the status of a Recommend task · Check task status #
Ask an LLM
“How can I tell whether my Recommend rule deletion has finished?”
“Is a Recommend task still pending or already published?”
Tell an agent
Check the status of Recommend task {taskID} for model {model} on {indexName}.
Tell me if recommendation task {taskID} on index {indexName} ({model}) is done.
POST /1/indexes/{indexName}/{model}/recommend/rules/search Search Recommend rules for a scenario · Search for rules #
Ask an LLM
“How do I list all the rules on a recommendation scenario?”
“Can I search Recommend rules by text and only show enabled ones?”
Tell an agent
List every Recommend rule for model {model} on index {indexName}.
Search {indexName}'s {model} recommendation rules for {query}.
POST /1/indexes/{indexName}/{model}/recommend/rules/batch Create or update Recommend rules in bulk · Create or update a batch of Recommend Rules #
Ask an LLM
“How can I create or update many Recommend rules in one request?”
“Can I atomically replace all existing rules on a recommendation scenario?”
Tell an agent
Upload a batch of Recommend rules to model {model} on index {indexName}.
Create or update several recommendation rules at once for {indexName}'s {model} scenario.
GET /setClientApiKey Switch the API key the Recommend client uses · Switch the API key used to authenticate requests #
Ask an LLM
“Can I change which API key my Recommend client authenticates with without recreating it?”
“Is it possible to rotate the key used for recommendation calls at runtime?”
Tell an agent
Switch the Recommend client to authenticate with API key {apiKey}.
Use {apiKey} as the key for subsequent Recommend requests.

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/algolia:algolia-recommend-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 form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

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

OpenAPI Specification

algolia-recommend-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: Recommend API
  summary: The Recommend API lets you retrieve recommendations from one of Algolia's AI recommendation models that you previously trained on your data
  description: '## Client libraries


    Use Algolia''s API clients and libraries to reliably integrate Algolia''s APIs with your apps.'
  version: 1.0.0
servers:
- url: https://{appId}.algolia.net
  variables:
    appId:
      default: ALGOLIA_APPLICATION_ID
- url: https://{appId}-1.algolianet.com
  variables:
    appId:
      default: ALGOLIA_APPLICATION_ID
- url: https://{appId}-2.algolianet.com
  variables:
    appId:
      default: ALGOLIA_APPLICATION_ID
- url: https://{appId}-3.algolianet.com
  variables:
    appId:
      default: ALGOLIA_APPLICATION_ID
- url: https://{appId}-dsn.algolia.net
  variables:
    appId:
      default: ALGOLIA_APPLICATION_ID
security:
- appId: []
  apiKey: []
tags:


# --- truncated at 32 KB (115 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/algolia/refs/heads/main/openapi/algolia-recommend-api-openapi.yml