Langbase

Embed API v1

The embed API endpoint allows you to generate vector embeddings for text chunks. This is particularly useful for semantic search, text similarity comparisons, and other NLP tasks.

Limitations

  • Maximum number of chunks per request: 100
  • Maximum length per chunk: 8192 characters
  • Available embedding models:
    • openai:text-embedding-3-large
    • cohere:embed-multilingual-v3.0
    • cohere:embed-multilingual-light-v3.0
    • google:text-embedding-004

Generate a User/Org API key

You will need to generate an API key to authenticate your requests. For more information, visit the User/Org API key documentation.

Embedding Models API Keys

Please add the LLM API keys for the embedding models you want to use in your API key settings.

POST/v1/embed

Generate embeddings

Generate vector embeddings for text chunks by sending them to the embed API endpoint.

Headers

  • Name
    Content-Type
    Type
    string
    Required
    Required
    Description

    Request content type. Needs to be application/json.

  • Name
    Authorization
    Type
    string
    Required
    Required
    Description

    Replace <YOUR_API_KEY> with your user/org API key.

Request Body

  • Name
    chunks
    Type
    string[]
    Required
    Required
    Description

    An array of text chunks to generate embeddings for. Maximum 100 chunks per request, with each chunk limited to 8192 characters.

  • Name
    embeddingModel
    Type
    string
    Description

    The embedding model to use. Available options:

    • openai:text-embedding-3-large
    • cohere:embed-multilingual-v3.0
    • cohere:embed-multilingual-light-v3.0
    • google:text-embedding-004

    Default: openai:text-embedding-3-large

Usage example

Install the SDK

npm i langbase

Environment variables

.env file

LANGBASE_API_KEY="<USER/ORG-API-KEY>"

Generate embeddings

Embedding

POST
/v1/embed
import { Langbase } from 'langbase';

const langbase = new Langbase({
  apiKey: process.env.LANGBASE_API_KEY!,
});

async function main() {
  const embeddings = await langbase.embed({
    chunks: [
      "The quick brown fox",
      "jumps over the lazy dog"
    ]
  });

  console.log('Embeddings:', embeddings);
}

main();

Response

  • Name
    Response
    Type
    number[][]
    Description

    The response is a 2D array where each inner array represents the embedding vector for the corresponding input chunk.

    Embed API Response

    type EmbedResponse = number[][];

API Response

[
  [-0.023, 0.128, -0.194, ...],
  [0.067, -0.022, 0.289, ...],
]