-
Notifications
You must be signed in to change notification settings - Fork 2.6k
Closed as not planned
Labels
Issue - In ProgressSomeone is actively working on this. Should link to a PR soon.Someone is actively working on this. Should link to a PR soon.enhancementNew feature or requestNew feature or requestproposal
Description
What specific problem does this solve?
As of now embedding providers list do not support using embedding models from Google Vertex AI.
Additional context (optional)
No response
Roo Code Task Links (Optional)
No response
Request checklist
- I've searched existing Issues and Discussions for duplicates
- This describes a specific problem with clear impact and context
Interested in implementing this?
- Yes, I'd like to help implement this feature
Implementation requirements
- I understand this needs approval before implementation begins
How should this be solved? (REQUIRED if contributing, optional otherwise)
Add option to select and use embedding models from Google Vertex AI.
How will we know it works? (Acceptance Criteria - REQUIRED if contributing, optional otherwise)
When user wants to select a embedding model from Google Vertex AI
Then user can choose Google Vertex AI embedding models
Technical considerations (REQUIRED if contributing, optional otherwise)
It is very similar to having "GCP Vertex AI" option in "API Provider". The UI will look similar to ./webview-ui/src/components/settings/providers/Vertex.tsx. Implementation should be easy. The implementation will be similar to ./src/services/code-index/embedders/gemini.ts.
Trade-offs and risks (REQUIRED if contributing, optional otherwise)
Use @google/genai library and follow google documentation https://ai.google.dev/gemini-api/docs/embeddings#javascript
Metadata
Metadata
Assignees
Labels
Issue - In ProgressSomeone is actively working on this. Should link to a PR soon.Someone is actively working on this. Should link to a PR soon.enhancementNew feature or requestNew feature or requestproposal
Type
Projects
Status
Done