未命名接口

POST

https://ark.cn-beijing.volces.com/api/v3/embeddings/multimodal

Doubao-embedding-vision 图文向量化模型是一款字节跳动研发的图文向量化模型，是一种支持文本、图片及图文混合输入的向量化技术，适用于文搜图、图搜图、图文混合搜索等场景。

请求参数

Authorization

Bearer Token

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Body 参数application/json

示例

返回响应

🟢200成功

application/json

Body

请求示例

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://ark.cn-beijing.volces.com/api/v3/embeddings/multimodal' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "doubao-embedding-vision-241215",
    "input": [
        {
            "type":"text",
            "text":"天很蓝，海很深"
        },
        {    
            "type":"image_url",
            "image_url":{
                "url":"https://ark-project.tos-cn-beijing.volces.com/images/view.jpeg"
            }
        }
      ]
}'

响应示例

{
    "id": "021718067849899d92fcbe0865fdffdde********************",
    "created": 171806****,
    "object": "list",
    "model": "doubao-embedding-***-******",
    "data": [
        {
            "object": "embedding",
            "embedding": [[0.62109375,-0.69140625,...,0.38671875]
        }
    ],
    "usage": {
        "prompt_tokens": 1340,
        "total_tokens": 1340,
        "prompt_tokens_details": {
            "text_tokens": 1312,
            "image_tokens": 28
        }
    }
}

修改于 2025-09-02 13:08:16

文本向量化 API