1jehuang / 1jehuang/jcode

Add Voyage AI embedding backend for memory retrieval

Open
#673 3 comments 0 reactions 0 assignees View on GitHub

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_KEY via env or voyage.env; keyless remote degrades to local
  • Honors Voyage input_type (query/document) and output_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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.