How to extract custom entities in text content with Python?

How to extract custom entities in text content with Python?

In this tutorial, you will learn how to use Custom Named Entity Recognition API in 5 minutes with Python. Eden AI provides an easy and developer-friendly API that allows you to extract specific entities into text.

What is Custom Named Entity Recognition API?

Custom Named Entity Recognition (NER) API is a tool that enables users to build and deploy their own models for recognizing and extracting named entities from text such as names of people, organizations, locations, dates, or any other custom-defined categories.

NER result on Eden AI

With a Custom NER API, users can train their models using their own labeled data, defining the specific entities they want to extract. This customization allows for a more tailored and accurate identification of entities that are relevant to a particular domain, industry, or specific use case. Once the model is trained, the API provides an interface for developers to integrate the custom NER functionality into their applications or systems.

Get Started with Custom NER API

The first step to getting started with Custom NER is to install Python's requests package, that will allow you to call Eden AI API.

Next, you'll need to install Python's JSON package to be able to read and print the result of the API request.

How to extract specific entities in text with Python

You are now ready to process your file into Eden AI Custom NER API.

1. Get an Custom NER API Key on Eden AI

To perform Custom NER, you'll need to create an account on Eden AI for free. Then, you will be able to get your API key directly from the homepage with free credits offered by Eden AI.

Eden AI platform - Get your API key

2. Let’s extract specific entities in text

Now that you have imported packages on Python and got your API key, you will be able to extract specific entities in your texts. With Eden AI, you can choose from a wide range of different engines you want for Custom NER. You can access the list of Custom NER providers available on Eden AI on our documentation here.

Here is the Python script you need to write on your notebook:

For example, we called two different Custom NER engines. Eden AI API will then return in its JSON response results of those providers.

Once the request is done, you will be able to get the result with this print:

Here is an example of a result for Custom NER task:

Benefits of using Custom NER API with Eden AI

Using Custom Named Entity Recognition with Eden AI API is quick and easy.

Multiple AIs in one API - Eden AI
Multiple AIs in one API - Eden AI

Save time and cost

We offer a unified API for all providers: simple and standard to use, with a quick switch between providers and an access to the specific features of each provider.

Easy to integrate

The JSON output format is the same for all suppliers thanks to Eden AI's standardisation work. The response elements are also standardised thanks to Eden AI's powerful matching algorithms.


With Eden AI you have the possibility to integrate a third party platform: we can quickly develop connectors. To go further and customize your Custom NER request with specific parameters, check out our documentation.

Related Posts

Try Eden AI for free.

You can directly start building now. If you have any questions, feel free to schedule a call with us!

Get startedContact sales