voyage-law-2

circle-info

This documentation is valid for the following list of our models:

  • voyage-law-2

Model Overview

This model leads the MTEB leaderboard for legal retrieval by a significant margin, outperforming OpenAI v3 large by an average of 6% across eight legal retrieval datasets and by over 10% on three key benchmarks (LeCaRDv2, LegalQuAD, and GerDaLIR). With a 16K context length and training on extensive long-context legal documents, voyage-law-2 excels in retrieving information across lengthy texts. Notably, it also matches or surpasses performance on general-purpose corpora across domains.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guidearrow-up-right.

API Schema

post
Authorizations
AuthorizationstringRequired

Bearer key

Body
modelundefined · enumRequiredPossible values:
inputany ofRequired

Input text to embed, encoded as a string or array of tokens.

string · min: 1 · max: 8000Optional
or
string[]Optional
input_typestring · enumOptional

The type of input data for the model.

Default: documentPossible values:
Responses
post
/v1/embeddings
201Success

No content

Code Example

This example shows how to set up an API client, send text to the embedding API, and print the response with the embedding vector. See how large a vector response the model generates from just a single short input phrase.

chevron-rightResponsehashtag

You can find a more advanced example of using embedding vectors in our article Find Relevant Answers: Semantic Search with Text Embeddings in the Use Cases section.

Last updated

Was this helpful?