Mixedbread AI integration

The MixedbreadAIEmbeddings class uses the Mixedbread AI API to generate text embeddings. This guide will walk you through setting up and using the MixedbreadAIEmbeddings class, helping you integrate it into your project effectively.

Installation

To install the @langchain/mixedbread-ai package, use the following command:

npm install @langchain/mixedbread-ai @langchain/core

Initialization

First, sign up on the Mixedbread AI website and get your API key from Mixedbread AI. You can then use this key to initialize the MixedbreadAIEmbeddings class.

You can pass the API key directly to the constructor or set it as an environment variable (MXBAI_API_KEY).

Basic usage

Here’s how to create an instance of MixedbreadAIEmbeddings:

import { MixedbreadAIEmbeddings } from "@langchain/mixedbread-ai";

const embeddings = new MixedbreadAIEmbeddings({
  apiKey: "YOUR_API_KEY",
  // Optionally specify model
  // model: "mixedbread-ai/mxbai-embed-large-v1",
});

If the apiKey is not provided, it will be read from the MXBAI_API_KEY environment variable.

Generating embeddings

Embedding a single query

To generate embeddings for a single text query, use the embedQuery method:

const embedding = await embeddings.embedQuery(
  "Represent this sentence for searching relevant passages: Is baking fun?"
);
console.log(embedding);

Embedding multiple documents

To generate embeddings for multiple documents, use the embedDocuments method. This method handles batching automatically based on the batchSize parameter:

const documents = ["Baking bread is fun", "I love baking"];

const embeddingsArray = await embeddings.embedDocuments(documents);
console.log(embeddingsArray);

Customizing requests

You can customize the SDK by passing additional parameters.

const customEmbeddings = new MixedbreadAIEmbeddings({
  apiKey: "YOUR_API_KEY",
  baseUrl: "...",
  maxRetries: 6,
});

Error handling

If the API key is not provided and cannot be found in the environment variables, an error will be thrown:

try {
  const embeddings = new MixedbreadAIEmbeddings();
} catch (error) {
  console.error(error);
}

Related

• Embedding model conceptual guide
• Embedding model how-to guides