Langbase

Embed langbase.embed()

Embed, an AI Primitive by Langbase, allows you to convert text into vector embeddings. This is particularly useful for semantic search, text similarity comparisons, and other NLP tasks.

Embedding text into vectors enables you to perform complex queries and analyses that go beyond simple keyword matching. It allows you to capture the semantic meaning of the text, making it easier to find relevant information based on context rather than just keywords.

You can use the embed() function to generate vector embeddings for text chunks. This is particularly useful for semantic search, text similarity comparisons, and other NLP tasks.

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.

API reference

langbase.embed(options)

Generate embeddings by running the langbase.embed() function.

Function Signature

langbase.embed(options);

// with types
langbase.embed(options: EmbedOptions);

options

  • Name
    options
    Type
    EmbedOptions
    Description

    EmbedOptions Object

    	chunks: string[];
	embeddingModel?: EmbeddingModels;

    Following are the properties of the options object.

chunks

  • Name
    chunks
    Type
    string[]
    Required
    Required
    Description

    An array of text chunks to generate embeddings for.

embeddingModel

  • Name
    embeddingModel
    Type
    EmbeddingModels
    Description

    The embedding model to use. Available options:

    • openai:text-embedding-3-large
    • cohere:embed-v4.0
    • cohere:embed-multilingual-v3.0
    • cohere:embed-multilingual-light-v3.0
    • google:text-embedding-004

    EmbeddingModels Type

    type EmbeddingModels =
"openai:text-embedding-3-large" |
"cohere:embed-v4.0" |
"cohere:embed-multilingual-v3.0" |
"cohere:embed-multilingual-light-v3.0" |
"google:text-embedding-004";

Usage example

Install the SDK

npm i langbase

Environment variables

.env file

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

langbase.embed() examples

langbase.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

Response of langbase.embed() is a Promise<number[][]>.

EmbedResponse Type

type EmbedResponse = number[][];
  • Name
    response
    Type
    number[][]
    Description

    A 2D array where each inner array represents the embedding vector for the corresponding input chunk.

EmbedResponse Example

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