> ## Documentation Index
> Fetch the complete documentation index at: https://doc.xihuyun.com.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# 文本向量 Embeddings

> 生成文本嵌入向量

**POST** `/v1/embeddings`

## 请求参数

| 参数                | 类型              | 必填 | 说明                         |
| ----------------- | --------------- | -- | -------------------------- |
| `model`           | string          | 是  | 如 `text-embedding-3-small` |
| `input`           | string \| array | 是  | 需要向量化的文本                   |
| `encoding_format` | string          | 否  | `float` 或 `base64`         |

## 示例

```bash theme={null}
curl https://your-domain.com/v1/embeddings \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": "你好世界"
  }'
```

## 响应

```json theme={null}
{
  "object": "list",
  "data": [
    {"object": "embedding", "index": 0, "embedding": [0.0023, -0.017, ...]}
  ],
  "model": "text-embedding-3-small",
  "usage": {"prompt_tokens": 4, "total_tokens": 4}
}
```