Embeddings
将文本转换为向量嵌入,兼容 OpenAI Embeddings API。
POST https://api.wrouter.io/v1/embeddings请求体
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
model | string | ✓ | 如 text-embedding-3-small、text-embedding-3-large、bge-large-zh、qwen3-embedding |
input | string | string[] | number[][] | ✓ | 待嵌入文本,或文本数组(批量) |
encoding_format | string | "float"(默认)或 "base64" | |
dimensions | integer | 截断到指定维度(仅部分模型支持) |
响应
json
{
"object": "list",
"data": [
{"object": "embedding", "index": 0, "embedding": [0.0123, -0.0456, ...]}
],
"model": "text-embedding-3-small",
"usage": {"prompt_tokens": 8, "total_tokens": 8}
}示例
bash
curl https://api.wrouter.io/v1/embeddings \
-H "Authorization: Bearer $WROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "text-embedding-3-small",
"input": ["wrouter 让大模型调用更简单。", "今天天气真好。"]
}'python
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://api.wrouter.io/v1")
vec = client.embeddings.create(
model="text-embedding-3-large",
input="向量化一段文本",
dimensions=1024,
).data[0].embedding批量与限制
- 单次请求
input数组最大 2048 条 - 单条文本最大 8192 tokens(具体取决于模型)
- 超长文本请客户端先切片再分批调用