Add Voyage AI embedding backend for memory retrieval
Open
Nobody has claimed this yet.
autonomous: no
enhancement
priority: low
triage: needs-decision
- Dominant language
- Rust
- Stars
- 19.9k
- Forks
- 2.3k
- Avg merge
- 2d 7h
- Merged PRs (30d)
- 30
Description
Memory dense-retrieval currently supports local and openai embedding backends. Proposal: add voyage as a third option (Voyage AI /v1/embeddings), mirroring the OpenAI backend.
- Configurable model / base-URL / dimension (reuses existing
memory_embedding_*config fields; no new fields) VOYAGE_API_KEYvia env orvoyage.env; keyless remote degrades to local- Honors Voyage
input_type(query/document) andoutput_dimension - Default model
voyage-code-3(not hardcoded) - Separate vector space (
voyage:<model>model_id), so switching stays safe
voyage-code-3 is code-optimized, a natural fit for a coding agent's memory retrieval.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the existing local and OpenAI memory embedding backends and the memory_embedding_* configuration fields. Check how the /v1/embeddings integration handles input_type, output_dimension, API keys, and model_id; done means voyage supports the listed configuration and fallback behavior while keeping a separate voyage: vector space.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- ai, backend-api-design
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100