API: 创建嵌入请求 (Embeddings)

Create an Embedding

Converts input content into embedding vectors. Supports text, image URL/base64, and mixed lists.

端点:POST /v1/embeddings

Request Body

model (string, required)

对应模型名称。完整可用模型列表请查看 模型广场。

示例:"BAAI/bge-large-zh-v1.5"

input (string | array, required)

待嵌入的文本。可以是字符串或字符串数组。输入长度不得超过模型最大 token 限制,且不能为空字符串。每个模型的最大输入 token 数如下:

• BAAI/bge-large-zh-v1.5、BAAI/bge-large-en-v1.5、netease-youdao/bce-embedding-base_v1:512
• BAAI/bge-m3、Pro/BAAI/bge-m3:8192
• Qwen/Qwen3-Embedding-8B/4B/0.6B:32768

encoding_format (string)

返回的嵌入向量格式。可选值:float | base64。默认 float。

dimensions (integer)

输出嵌入向量的维度数,仅 Qwen/Qwen3 系列支持。

• Qwen/Qwen3-Embedding-8B:[64, 128, 256, 512, 768, 1024, 1536, 2048, 2560, 4096]
• Qwen/Qwen3-Embedding-4B:[64, 128, 256, 512, 768, 1024, 2048, 2560]

代码示例

cURL

curl --request POST \
  --url https://khb.net.cn/v1/embeddings \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "BAAI/bge-large-zh-v1.5",
    "input": "今天天气真不错"
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://khb.net.cn/v1"
)

response = client.embeddings.create(
    model="BAAI/bge-large-zh-v1.5",
    input="今天天气真不错"
)

vector = response.data[0].embedding
print(f"维度: {len(vector)}")
print(f"前 5 维: {vector[:5]}")

Response Body

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0123, -0.0456, 0.0789, ...]
    }
  ],
  "model": "BAAI/bge-large-zh-v1.5",
  "usage": {
    "prompt_tokens": 6,
    "total_tokens": 6
  }
}

错误码