Embeddings

POST/v1/embeddings

把文本或文本数组转换为向量表示。

向量维度、批量限制和可选字段由所选模型与 Provider 决定，请先从模型目录选择 embedding 能力模型。

核心请求字段

字段	类型	必填	说明
`model`	string	是	Embedding 模型 ID。
`input`	string \| array	是	需要向量化的文本或文本数组。
`encoding_format`	string	否	输出编码格式，仅在模型路由支持时使用。
`dimensions`	integer	否	目标维度，仅在模型路由支持时使用。

请求示例

curl https://api.noxgate.net/v1/embeddings \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"YOUR_MODEL_ID","input":["First document","Second document"]}'

from openai import OpenAI

client = OpenAI(api_key="sk-your-api-key", base_url="https://api.noxgate.net/v1")
response = client.embeddings.create(model="YOUR_MODEL_ID", input=["First document", "Second document"])
print(response.data[0].embedding)

import OpenAI from "openai";

const client = new OpenAI({ apiKey: "sk-your-api-key", baseURL: "https://api.noxgate.net/v1" });
const response = await client.embeddings.create({ model: "YOUR_MODEL_ID", input: ["First document", "Second document"] });
console.log(response.data[0].embedding);

成功响应

{"object":"list","data":[{"object":"embedding","index":0,"embedding":[0.012,-0.031,0.008]}],"model":"YOUR_MODEL_ID","usage":{"prompt_tokens":4,"total_tokens":4}}