Embeddings 向量 API

curl https://api-models.com/v1/embeddings \
  -H "Authorization: Bearer $API_MODELS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["第一篇文档", "第二篇文档"],
    "encoding_format": "float",
    "dimensions": 256
  }'

import os
import requests

response = requests.post(
    "https://api-models.com/v1/embeddings",
    headers={"Authorization": f"Bearer {os.environ['API_MODELS_KEY']}"},
    json={
        "model": "text-embedding-3-large",
        "input": ["第一篇文档", "第二篇文档"],
        "encoding_format": "float",
        "dimensions": 1024,
    },
    timeout=120,
)
response.raise_for_status()
vectors = [item["embedding"] for item in response.json()["data"]]
print(len(vectors), len(vectors[0]))

const response = await fetch("https://api-models.com/v1/embeddings", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.API_MODELS_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "text-embedding-3-small", input: ["第一篇文档", "第二篇文档"], encoding_format: "float", dimensions: 256 }),
});
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
console.log(result.data.map((item) => item.embedding.length));