feat(ai-gateway): Align semantic similarity documentation with AI GW 2.0#5501
feat(ai-gateway): Align semantic similarity documentation with AI GW 2.0#5501tomek-labuk wants to merge 10 commits into
Conversation
✅ Deploy Preview for kongdeveloper ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
There was a problem hiding this comment.
Pull request overview
Updates the AI Gateway semantic similarity reference to reflect AI Gateway 2.0 concepts (Models and Policies) instead of the older plugin-centric framing.
Changes:
- Refocuses the page around AI Gateway 2.0 semantics (Model semantic load balancing + semantic Policies) and updates related links to entity docs.
- Rewrites the “vector databases” and “similarity application” sections to describe Model/policy behavior rather than individual plugins.
- Updates configuration field references from plugin-centric wording to policy-centric wording.
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
|
|
| When a plugin needs to find semantically similar content—whether it’s a past prompt, an upstream description, or a document chunk—it sends a query to a vector database. The database returns the closest matches, allowing the plugin to make decisions like caching, routing, injecting, or blocking. | ||
| When a Model’s semantic load balancer or an attached semantic policy needs to find semantically similar content—whether it’s a prompt, a target model description, or a document chunk—it sends a query to a vector database. The database returns the closest matches, allowing the Model or policy to make decisions like routing, caching, injecting, or blocking. | ||
|
|
||
| {% include_cached /plugins/ai-vector-db.md name=page.name %} |
There was a problem hiding this comment.
Why was the include of supported vector DBs removed, this is important and often requested information
There was a problem hiding this comment.
It was my mistake, I restored it
|
|
||
| The following table describes how each AI plugin compares embeddings: | ||
| **Model semantic load balancing** (`semantic` algorithm): | ||
| - Compares incoming prompt embeddings against stored embeddings of each target model's semantic description. |
There was a problem hiding this comment.
Is this the complete description? Based on my knowledge the described process would not have great results.
There was a problem hiding this comment.
I've improved this one, Does it look okay now?
|
As an aside the intro is very clunky and could be rewritten |
Co-authored-by: jbaross <james.baross@konghq.com>
Yeah, that's true. I've fixed it as well |
Description
Updates the AI Gateway semantic similarity reference to reflect AI Gateway 2.0 concepts (Models and Policies) instead of the older plugin-centric framing.
Changes:
Refocuses the page around AI Gateway 2.0 semantics (Model semantic load balancing + semantic Policies) and updates related links to entity docs.
Rewrites the “vector databases” and “similarity application” sections to describe Model/policy behavior rather than individual plugins.
Updates configuration field references from plugin-centric wording to policy-centric wording.
Preview Links
https://deploy-preview-5501--kongdeveloper.netlify.app/ai-gateway/semantic-similarity/
Checklist
descriptionentry in frontmatter.