---
description: "与 OpenAI 兼容的 Embeddings 文本向量接口。"
---

# Embeddings

> 端点: `POST https://oneapi.zaiwenai.com/v1/embeddings`

与 OpenAI Embeddings 接口兼容，用于将文本转换为向量表示。

## 请求参数

| 参数 | 类型 | 必填 | 说明 |
|------|------|------|------|
| `model` | string | 是 | 模型名称 |
| `input` | string \| string[] | 是 | 要嵌入的文本，支持单个字符串或字符串数组 |
| `encoding_format` | string | 否 | 返回格式，`float`（默认）或 `base64` |
| `dimensions` | integer | 否 | 指定输出向量维度 |

## Curl 示例

```bash
curl https://oneapi.zaiwenai.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "bge-m3",
    "input": "Hello, world!"
  }'
```

## OpenAI Python SDK 示例

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://oneapi.zaiwenai.com/v1",
    api_key="$YOUR_API_KEY",
)

response = client.embeddings.create(
    model="bge-m3",
    input="Hello, world!",
)

print(response.data[0].embedding)
```

## 批量输入示例

```python
response = client.embeddings.create(
    model="bge-m3",
    input=["Hello", "World", "Embeddings"],
)

for item in response.data:
    print(f"Index {item.index}: {len(item.embedding)} dimensions")
```

## 响应格式

```json
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.0023064255, -0.009327292, ...],
      "index": 0
    }
  ],
  "model": "bge-m3",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}
```