AI Assistant - Sending requests too quickly

Problem

While using your ADONIS AI Assistant with OpenAI as AI provider., you may encounter the following error message:

"ERROR - You are sending requests too quickly or transmitting too much data at once. Please slow
down and try again in a moment."

Cause

You have exceeded the maximum quota permitted by your OpenAI contract. The base configuration of BOC AI Assistant is correct, as this message is generated directly by OpenAI.
 
In OpenAI terminology, a “quota” refers to the number of requests or amount of text (tokens) your account is authorized to use within a specified time frame. 

This mechanism is implemented to maintain fairness and system stability by restricting the number of requests you may submit per minute or per day, as well as the volume of text the AI can process simultaneously.

Solution

To quickly check your current quota and usage, contact your internal AI administrator, as details on this exact topic can be found on OpenAI Documentation: Rate limits | OpenAI API 

The exact limit could be displayed under OpenAI Usage, OpenAI Rate-Limits or a specific company portal.