OpenAI Embeddings API: How to change the embedding output dimension?

Question

In the official OpenAI node library Create embeddings if for example using the model text-embedding-ada-002 the embeddings returned is an array of around 1536.

import {Configuration, OpenAIApi} from 'openai'

openai = new OpenAIApi(this.configuration)
const parameters= {
      model: 'text-embedding-ada-002',
      input: text,
    }
// Make the embedding request and return the result
const resp = await openai.createEmbedding(parameters)
const embeddings = embedding?.data.data[0].embedding

I would like to be able to limit the length of the list of embeddings returned.

Rok Benko · Accepted Answer · 2024-06-12 16:40:26Z

2

You need to use the dimensions parameter with the OpenAI Embeddings API.

As stated in the official OpenAI documentation:

By default, the length of the embedding vector will be 1536 for text-embedding-3-small or 3072 for text-embedding-3-large. You can reduce the dimensions of the embedding by passing in the dimensions parameter without the embedding losing its concept-representing properties. We go into more detail on embedding dimensions in the embedding use case section.

edited Jun 12, 2024 at 16:40

answered Mar 14, 2023 at 13:32

Rok Benko

23.7k5 gold badges41 silver badges73 bronze badges

Sign up to request clarification or add additional context in comments.

5 Comments

Nadsah Over a year ago

Okay thank you, for the clarification! so if I want a Limited numbers of embeddings I will have to use some other tokenizer?

Rok Benko Over a year ago

Yes, you need to use any other Python library where you have an option to choose the embedding output dimension. This looks promising. Seems like you can set vector_size.

kumail Over a year ago

Is there a way to take the top n most relevant embeddings out of the 1536 in the output dimension?

Rok Benko Over a year ago

@kumail You can't simply "take the top n most relevant embeddings out of the 1536". You don't get 1536 embeddings from the OpenAI Embeddings API. You get one(!) 1536-dimensional embedding. Anyway, what you can try to do is translate the embedding you get from the OpenAI Embeddings API to a lower-dimensional space. I edited my answer.

theterminalguy Over a year ago

OpenAi now supports a dimension parameter

Collectives™ on Stack Overflow

OpenAI Embeddings API: How to change the embedding output dimension?

1 Answer 1

5 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

5 Comments

Your Answer

Sign up or log in

Post as a guest

Related