题意：OpenAI Embeddings API：如何更改嵌入输出维度？

问题背景：

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.

在官方的 OpenAI Node.js 库中，如果使用 text-embedding-ada-002 模型创建嵌入，返回的嵌入是一个长度大约为 1536 的数组。

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.

我希望能够限制返回的嵌入列表的长度。

问题解决：

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

你需要在 OpenAI Embeddings API 中使用 dimensions 参数。

As stated in the official OpenAI documentation:

正如官方 OpenAI 文档中所述：

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.