Voyage-3
used in
1
stack
General-purpose text embedding model tuned for retrieval quality.
General-purpose embedding model from Voyage AI (now part of MongoDB), commonly used to power the retrieval layer of RAG agents. API-based; pairs with a vector store such as Pinecone, pgvector, or turbopuffer.
Strengths
- Strong retrieval quality on general-domain text
- API-based; no embedding infrastructure to host
Tradeoffs
- API-only; document text leaves your environment to be embedded
- Adds a second vendor alongside the generation model