Sign in
Embedding Modeltext_to_embeddingVoyage Embeddings Family

Voyage Law Embeddings

Voyage Law Embeddings is a domain-specialized text embedding model optimized for legal documents, case law, contracts, and regulatory text. It is designed to power high-accuracy semantic search, retrieval-augmented generation (RAG), and clustering in legal and compliance workflows.

by Voyage AI
API Access
Available

Key Capabilities

  • +Domain-specialized embeddings for legal and regulatory text
  • +High-quality semantic search and retrieval for case law and contracts
  • +Support for retrieval-augmented generation (RAG) pipelines
  • +Clustering and deduplication of large legal corpora
  • +Multilingual or cross-jurisdiction legal text handling (where supported by the model)

Limitations

  • -Benchmarks and architecture details are not fully public, limiting comparability
  • -Likely optimized for legal text and may underperform on general-domain content
  • -Embedding dimensionality and context limits may constrain extremely long filings or multi-document inputs
  • -Closed, proprietary service with no access to training data or weights

Benchmark Performance

embedding

embedding

Massive Text Embedding Benchmark

62.6%
embedding

MTEB Retrieval Average

51.2%

Sources

voyageai.comdocs.voyageai.com