[Feature]: First-class "Embedding & Vector Store Providers" resource, reusable across Semantic Cache and future embedding-based policies #3418

Please select the area the issue is related to

AI Workspace, Gateway

Please select the aspect the issue is related to

Aspect/UI (Frontend layouts, components, styling), Aspect/Configuration (Config files, settings, env vars, defaults)

Suggested Feature

Embedding provider and vector DB settings needed for Semantic Cache (embedding_provider, embedding_provider_dimension, embedding_provider_api_key, vector_db_provider, vector_db_provider_host, etc.) currently live as flat keys in the gateway's config.toml, with no Console UI to manage them. The current key structure appears to only support a single embedding provider and vector store — there's no confirmed support for configuring more than one.

Suggest adding "Embedding & Vector Store Providers" as a first-class, UI-managed resource, following the same pattern already used for "LLM Providers": configure once (endpoint, auth, model, dimension / host, port, credentials), then select from a dropdown wherever needed, instead of editing config files directly.

This would also support multiple named providers, so different use cases (e.g. a cheaper model for high-volume caching vs. a stricter one elsewhere) aren't forced to share one global config.

Semantic Cache is a confirmed consumer of this config today. A shared, reusable resource would avoid re-solving the same config problem if similar embedding-based features (e.g. semantic guardrails, semantic routing) are added later.

Related Issues

#3417

Steps to Verify

• Design Document — A detailed design document has been created and reviewed, covering architecture, data flow, and edge cases.
• Design Mail — A design summary email has been sent to relevant stakeholders for awareness and feedback.
• Code Review — All code changes have been peer-reviewed and approved according to the project's review standards.
• Testing Complete — Adequate unit, integration, and/or end-to-end tests have been written and are passing.
• Documentation Review — User-facing and/or developer documentation has been updated to reflect the new feature and reviewed.
• Feature Complete — The feature is fully implemented, all checklist items above are done, and it is ready for release.