Wingman
2.1.0
2.1.0
  • Introduction
  • Functional Details
  • Configuration
    • 2.1.0 configuration
    • Service Provider & Model ID Details
    • Backend Configurations
  • AI Service Data Security Details
    • AWS Bedrock
  • Change Log
  • Model List
Powered by GitBook
On this page
  1. Configuration

Backend Configurations

To set the backend limit on total token consumption and percentage it to send trigger is configured through these keys:

  1. tokenConsumptionLimit - This is the key against which the total tokens for the AI service is set.

  2. tokenConsumptionTrigger - This is the key against which the percentage value of the above key is set. When that percentage consumption is breached, a trigger will be set to true in the API response.

PreviousService Provider & Model ID DetailsNextAI Service Data Security Details