As a platform that allows the easy use of NLP in applications, Weni's integration process with external services is very simple!

In this article, you will learn how to Integrate with the prediction API to be able to access your intelligence from other platforms via HTTP requests.


Go to your intelligence and click on the Integration section

To make an HTTP request to the prediction API, you will need the following information:

  • Protocol: the API uses the HTTP protocol.
  • Base URL: the URL used for all the requests. The current base URL for the API is
  • Header: is the authorization token, used for integrate with a intelligence. Every intelligence has a unique token that needs to be passed on the header of the request.
  • Request Body: the body needs to have the language and text for the intelligence to predict it.
  • Response: is the JSON format of the response from BotHub, after a request is successfully made.

Code generator

The Code generator is a very useful tool, which allows the user to simulate a request in the syntax of technologies such as cURL, Python and Javascript. Select the prediction's language and text and an example of a request will appear.

After that, copy the example and start testing your intelligence through the API!

How did we do?


Integrate an intelligence to your project in the Weni Platform