Skip to content

Commit

Permalink
Revert #8183 (#8222)
Browse files Browse the repository at this point in the history
* Revert "Update _index.md"

This reverts commit 767303b.

* Revert "support for multiple limits and window sizes"

This reverts commit be5fe36.
  • Loading branch information
fabianrbz authored Dec 4, 2024
1 parent 348f50a commit 633e1e1
Showing 1 changed file with 0 additions and 13 deletions.
13 changes: 0 additions & 13 deletions app/_hub/kong-inc/ai-rate-limiting-advanced/how-to/_index.md
Original file line number Diff line number Diff line change
Expand Up @@ -32,26 +32,13 @@ curl -i -X POST \

Protect your LLM service with rate limiting. It will analyze query costs and token response to provide an enterprise-grade rate limiting strategy.

{% if_version lte:3.8.x %}
```sh
curl -i -X POST http://localhost:8001/services/example-service/plugins \
--data 'name=ai-rate-limiting-advanced' \
--data 'config.llm_providers[1].name=openai' \
--data 'config.llm_providers[1].limit=100' \
--data 'config.llm_providers[1].window_size=3600'
```
{% endif_version %}
{% if_version gte:3.9.x %}
```sh
curl -i -X POST http://localhost:8001/services/example-service/plugins \
--data 'name=ai-rate-limiting-advanced' \
--data 'config.llm_providers[1].name=openai' \
--data 'config.llm_providers[1].limit[]=100' \
--data 'config.llm_providers[1].limit[]=10000' \
--data 'config.llm_providers[1].window_size[]=60 \
--data 'config.llm_providers[1].window_size[]=3600'
```
{% endif_version %}

The AI Rate Limiting Advanced plugin supports threes rate limiting strategies. The default strategy will estimate cost on queries by counting the total token value returned in the LLM responses.

Expand Down

0 comments on commit 633e1e1

Please sign in to comment.