Welcome to my video about the AI Rate Limiting plugin for the Kong Gateway. This plugin allows us to control traffic to our AI configuration with the AI proxy configuration. If you missed the AI-Proxy video, and you are figuring out what to do with it or just want to know more, then perhaps one good thing to do is to checkout the first video I made about Kong's AI plugins over here: https://youtu.be/6Z8wWX-liBs . This particular vide, the AI Advanced Rate Limiting plugin, makes more sense to use, if we are using multiple LLM models under different routes common services. It allows for a seamless configuration and better cost controls. I tell all the basics in the video. I hope you enjoy the video and be sure to stay tech, keep programming, be kind and have a good on everyone!
---
Chapters:
00:00:00 Start 00:00:33 Introduction 00:03:19 Configuring Mistral AI 00:04:59 The AI Advanced Rate Limiting Plugin in Detail 00:09:19 Interpreting Rate Limiting Headers 00:10:32 Checking out the configuration in Kong Konnect 00:11:07 Talking about Kong Semantic AI Cache - https://youtu.be/b3dAMZOhr58 00:11:31 Checking out the example 00:12:10 Getting back to the AI Semantic Cache plugin - https://youtu.be/b3dAMZOhr58 00:15:02 Launching examples and interpreting results 00:20:39 End notes and conclusion 00:21:22 See you in the next video! 00:22:11 Disclaimer
As a short disclaimer, I'd like to mention that I'm not associated or affiliated with any of the brands eventually shown, displayed, or mentioned in this video.
---
All my work and personal interests are also discoverable on other different sites:
If you have any questions about this video please put a comment in the comment section below and I will be more than happy to help you or discuss any related topic you'd like to discuss.
