Skip to content

Add more model support for token rate-limiting #14

@stuartleeks

Description

@stuartleeks

The changes in stuartleeks/aoai-simulated-api#51 align the rate-limiting behaviour with PAYG deployments for text-embedding-ada-002, text-embedding-3-small. text-embedding-3-large, and gpt-3.5-turbo.

Other models should be investigated and added to the handling

(from stuartleeks/aoai-simulated-api#52)

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions