voyage-multilingual-2

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

• voyage-multilingual-2

Model Overview

Optimized for multilingual retrieval and retrieval-augmented generation (RAG), this model surpasses alternatives like OpenAI v3 large and Cohere multilingual v3 across most languages, including French, German, Japanese, Spanish, and Korean. On average, it outperforms the second-best model by 5.6%, while maintaining strong performance in English. Additionally, it supports a large 32K context length.

Setup your API Key

If you don’t have an API key for the Apilaplas API yet, feel free to use our Quickstart guide.

Submit a request

API Schema

post

Authorizations

Body

modelundefined · enumRequiredPossible values:

inputany ofRequired

string · min: 1 · max: 8000Optional

or

string[]Optional

input_typestring · enumOptionalDefault: documentPossible values:

encoding_formatstringOptional

Responses

201Success

post

HTTPcURLJavaScriptPython

POST /v1/embeddings HTTP/1.1
Host: api.apilaplas.com
Authorization: Bearer <YOUR_LAPLASAPI_KEY>
Content-Type: application/json
Accept: */*
Content-Length: 97

{
  "model": "voyage-multilingual-2",
  "input": "text",
  "input_type": "document",
  "encoding_format": "text"
}

201Success

No content