feat(ai-gateway): Update load balancing capabilities documentation for AI Gateway 2.0#5308
feat(ai-gateway): Update load balancing capabilities documentation for AI Gateway 2.0#5308tomek-labuk wants to merge 8 commits into
Conversation
There was a problem hiding this comment.
Pull request overview
This PR updates the AI Gateway documentation to reflect the AI Gateway 2.0 load balancing workflow (Model entity-based configuration) while preserving legacy AI Proxy Advanced plugin-based guidance for existing deployments.
Changes:
- Updates the
/ai-gateway/load-balancing/reference to describe Model entity load balancing (config.balancer/target_models) and adds a legacy algorithms section behind a<details>block. - Adds a new include containing the legacy (plugin-based) load balancing algorithms table.
- Expands the Model entity reference with a clearer capabilities table, a deeper TOC, and new per-algorithm Model entity examples.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 6 comments.
| File | Description |
|---|---|
| app/ai-gateway/load-balancing.md | Reframes load balancing docs around Model entities (AI Gateway 2.0) and nests legacy plugin guidance. |
| app/_includes/ai-gateway/load-balancing/legacy-algorithms.md | Adds a legacy, plugin-focused algorithms table for older configurations. |
| app/_ai_gateway_entities/model.md | Enhances the Model entity reference (capabilities table, TOC depth, and new algorithm examples). |
| @@ -182,6 +207,8 @@ rows: | |||
|
|
|||
| You can customize {{site.ai_gateway}} load balancer to fit different application needs, such as minimizing latency, enabling sticky sessions, or optimizing for cost. The table below maps common scenarios to key configuration options that control load balancing behavior: | |||
|
|
|||
| #### Retry and fallback scenarios for Model entities {% new_in 2.0.0 %} | |||
|
|
|||
There was a problem hiding this comment.
Fixed in 9f9206c — removed the redundant "Retry and fallback scenarios" heading and folded the intro text under the single "Retry and fallback scenarios for Model entities" heading.
| {% include plugins/ai-vector-db.md name="Model entity" %} | ||
|
|
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Agent-Logs-Url: https://github.com/Kong/developer.konghq.com/sessions/595adc85-e769-4186-be95-c55b10555c43 Co-authored-by: tomek-labuk <207846229+tomek-labuk@users.noreply.github.com>
|
|
Agent-Logs-Url: https://github.com/Kong/developer.konghq.com/sessions/48dc16c7-dd94-4eba-a278-8b86428fe326 Co-authored-by: tomek-labuk <207846229+tomek-labuk@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Description
Notes:
Preview Links
Checklist
descriptionentry in frontmatter.