Generative AI

Making API Requests for Generative AI Results

All of the ElevateAI Generative AI API Endpoints use a similar format, leveraging the unique interactionIdentifier returned upon successfully declaring the ﻿audio﻿, ﻿transcript﻿, or ﻿chat﻿ interaction.
When the desired GET request* successfully executes, an HTTP status is returned to indicate the request was successful, along with a JSON response providing details specific to that endpoint.  Details specific to an individual endpoint are covered on the Generative AI API Endpoint Details﻿ page.
* All endpoints support a GET method.  The Ask ElevateAI endpoint supports both POST and GET methods.  See the documentation for that endpoint for details.
﻿
Following is the general request format to be used for all of the Generative AI API requests:
General request format
GET
Request
Path Params
interactionIdentifier
required
String
interactionIdentifier returned upon successfully declaring the interaction
endpoint
required
String
The specific API endpoint for the desired Generative AI response.  Endpoints are covered on the Generative AI API Endpoint Details page.
Header Parameters
X-API-Token
required
String
Valid API key associated with your account for authentication and usage tracking
Accept-Encoding
optional
String
Recommended for bandwidth optimization, will be 'gzip, deflate, br'
Accept-Language
optional
String
To be used for the Summary endpoint only (ignored for other endpoints).  Specify the language code for the desired language of the response (e.g. pt-BR).  Default is English.
Curl
Node.js
JS
Python
Ruby
var request = require('request');
var options = {
   'method': 'GET',
   'url': 'https://api.elevateai.com/v1/interactions/{interactionIdentifier}/{endpoint}',
   'headers': {
      'Accept': 'application/json',
      'Content-Type': 'application/json'
   }
};
request(options, function (error, response) {
   if (error) throw new Error(error);
   console.log(response.body);
});

var request = require('request');
var options = {
   'method': 'GET',
   'url': 'https://api.elevateai.com/v1/interactions/{interactionIdentifier}/{endpoint}',
   'headers': {
      'Accept': 'application/json',
      'Content-Type': 'application/json'
   }
};
request(options, function (error, response) {
   if (error) throw new Error(error);
   console.log(response.body);
});
Responses
200
404
408
409
422
429
500
504
{
  "errorMessage (string)"
}
{
  "errorMessage (string)"
}
﻿
﻿
Retryable Responses
The following response codes leave the interaction endpoint in a retryable state.  Calling code should handle these responses gracefully and retry appropriately.
Response
Message
Meaning
408
RequestTimeout
The Generative AI model was not able to respond in an acceptable amount of time.  
429
TooManyRequests
By default, each account is allowed up to 10 simultaneous Generative AI requests at one time.  This response indicates that more than 10 are being attempted.
﻿
﻿
﻿
﻿
﻿
﻿

Response	Message	Meaning
408	RequestTimeout	The Generative AI model was not able to respond in an acceptable amount of time.
429	TooManyRequests	By default, each account is allowed up to 10 simultaneous Generative AI requests at one time. This response indicates that more than 10 are being attempted.

ElevateAI Generative AI API calls

Generative AI API Endpoint Details