Skip to content

Embeddings ​

兼容 OpenAI Embeddings,把文本转换为向量,用于语义搜索、聚类和知识库检索。

POSThttps://api.codingrouter.ai/v1/embeddings

鉴权 ​

Authorization: Bearer <令牌>

请求参数 ​

参数类型必填说明
modelstring是text-embedding-3-small、text-embedding-3-large(az_gpt 分组),gemini-embedding-001(gemini 分组)
inputstring / array是一段文本,或文本数组
dimensionsinteger否输出维度,仅 text-embedding-3 系列支持

默认维度:text-embedding-3-small 1536,text-embedding-3-large 3072,gemini-embedding-001 3072。

请求示例 ​

bash
curl https://api.codingrouter.ai/v1/embeddings \
  -H "Authorization: Bearer $CODINGROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "text-embedding-3-small", "input": ["第一段文本", "第二段文本"]}'
python
from openai import OpenAI

client = OpenAI(base_url="https://api.codingrouter.ai/v1", api_key="sk-你的令牌")

resp = client.embeddings.create(model="text-embedding-3-small", input=["第一段文本", "第二段文本"])
print(len(resp.data[0].embedding))  # 1536
js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.codingrouter.ai/v1",
  apiKey: process.env.CODINGROUTER_KEY,
});

const resp = await client.embeddings.create({
  model: "text-embedding-3-small",
  input: ["第一段文本", "第二段文本"],
});
console.log(resp.data[0].embedding.length);

响应示例 ​

json
{
  "object": "list",
  "model": "text-embedding-3-small",
  "data": [
    {"object": "embedding", "index": 0, "embedding": [0.0292, 0.0104, -0.0091, "..."]},
    {"object": "embedding", "index": 1, "embedding": [0.0400, 0.0109, -0.0124, "..."]}
  ],
  "usage": {"prompt_tokens": 10, "total_tokens": 10}
}

data 与 input 顺序一一对应。