Entity Recognition — extract entities from text

AI Text Entity Recognition API

Hosted on ApyHub

What it does

Entity Recognition identifies names, organizations, places, and other entities in plain text. Send a text string in the request body, and choose whether to run it through requested_service set to azure, google, or apyhub.

Use it when you need to extract structured meaning from unstructured text. For example, you can process support tickets, news articles, CRM notes, or internal documents to find people, companies, and locations without writing your own NLP pipeline.

The response wraps provider-specific results under data.azure, data.google, or data.apyhub, depending on the service you request. That makes it useful when you want a single endpoint for entity detection while keeping the downstream response aligned with the NLP provider you choose.

If you already have language or encoding details, you can include language, encoding, or provider credentials in azure or google as needed. Entity Recognition is a fit for enrichment workflows, document processing, search indexing, and any automation that starts with free-form text.

Provider (requested_service)	Atoms
Azure	500
Google	500
ApyHub	2000

Quickstart

Recognize entities in a short text snippet with the default ApyHub service.

curl -X POST "http://localhost:8080/apyhub/recognize-entities-in-text" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Google was founded in 1998 by Larry Page and Sergey Brin.",
    "requested_service": "apyhub"
  }'

About this endpoint

What it does

Recognizes entities in a text string and returns a JSON object containing provider-specific results under data. You can submit the text and optionally provide Azure or Google credentials/configuration, then choose which service to use via requested_service or let it default to ApyHub.

Request Body

Parameter	Type	Mandatory	Description
text	String	Yes	Text to analyze for entity recognition.
azure	Object	No	Custom credentials for Azure services. See schema for nested fields.
azure.key	String	No	Azure subscription key.
azure.region	String	No	Azure service region.
azure.endpoint	String	No	Azure endpoint URL.
azure.account_id	String	No	Azure account ID.
azure.access_token	String	No	OAuth access token for Azure service.
google	Object	No	Custom credentials for Google services. See schema for nested fields.
google.google_language	String	No	Target language locale.
google.google_credential_json	Object	No	Google service account credential JSON. See schema for nested fields.
encoding	String	No	Text encoding.
language	String	No	Language code for the input text.
requested_service	ENUM	No	Service to use. Allowed values: `azure`, `google`, `apyhub`. Default: `apyhub`.

Response

Returns a JSON object with a data object field containing provider-specific result objects for azure, apyhub, and google. The schema defines these as top-level keys inside data, each represented as an object.

Parameter	Type	Mandatory	Description
data	Object	No	Container for provider-specific response objects.
data.azure	Object	No	Response object from Microsoft Azure Cognitive Services.
data.apyhub	Object	No	Response object from ApyHub language tools.
data.google	Object	No	Response object from Google Cloud NLP API.

Body

Name

Type

Description

bodyREQUIRED

object

—

AI Text Entity Recognition API

What it does

Quickstart

What you'll get back

About this endpoint

What it does

Request Body

Response

Body

Errors any endpoint can return