{"componentChunkName":"component---src-templates-acg-portal-new-template-tsx","path":"/vmh8u2gsu","result":{"data":{"markdownRemark":{"html":"\n
\n
\n
\n
\n
POST
\n
\nhttps://qianfan.baidubce.com/v2/embeddings\n
\n
\n\n \n调试\n\n
\n

根据输入内容生成对应的向量表示。

\n
\n
\n

支持模型列表

\n

支持模型列表请查看千帆ModelBuilder-模型列表-向量。

\n

注意事项

\n

（1）本文API，支持预置服务对应API和平台训练模型调用API。
（2）针对平台训练调用API，调用本文API前，需先经过SFT模型训练后发布服务，相关内容请参考新手指南-平台使用快速开始。

\n

权限说明

\n

调用本文API，需使用API Key鉴权方式。使用API Key鉴权调用API流程，具体调用流程，请查看认证鉴权。

\n
\n
\n

请求参数

\n
\n
\n
\n
\n
Headers 参数
\n
除公共头域外，无其它特殊头域
\n
\n
\n
\n
\n
Body 参数
\n
\n
\n
\n
\n
\n\nmodel\n\nstring\n
\n

模型ID，
（1）预置服务，可选值请参考千帆ModelBuilder-模型列表-向量页，表格中model入参列
（2）平台训练模型或预置模型，可以通过查看服务详情获取该字段值，详情请查看千帆控制台-在线推理：model值为服务详情中对应的API名称，如下图所示：
\"image.png\"

\n
\n
必选
\n
\n
\n
\n\ninput\n\nanyOf {2}\n

多选一，只需要符合下列任意一组子节点

\n
\n

输入内容

\n
\n
必选
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\ninput\n\nanyOf {2}\n

多选一，只需要符合下列任意一组子节点

\n
\n

输入文本以获取embeddings，支持字符串列表或字符串

\n
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\nanyOf-0\n\nstring\n
\n

不同模型每个文本限制如下：\n
· Embedding-V1：文本token数不超过384且长度不超过1000个字符
· bge-large-zh或bge-large-en：文本token数不超过512且长度不超过2000个字符
· tao-8k：文本token数不超过8192且长度不超过28000个字符
· Qwen3-Embedding-0.6B或Qwen3-Embedding-4B：每个文本token最多8k

\n
\n
\n
\n
\n\nanyOf-0\n\narray\n
\n

说明：
（1）不能为空List，List的每个成员不能为空字符串
（2）不同模型文本数量限制如下：
· tao-8k：文本数量只能为1
· 其它：文本数量不超过16
（3）不同模型每个文本限制，请参考上述不同模型每个文本限制说明

\n
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\nitems\n\nstring\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n\ninput\n\narray\n
\n

针对多模态向量模型，说明：
（1）input内元素支持输入三种组合：单个文本、单个图片或一对文本+图片
（2）input内只支持单元素，不支持批量元素向量化（3）适用模型：gme-Qwen2-VL-2B-Instruct

\n
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\nitems\n\nobject {2}\n
\n
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\ntext\n\nstring\n
\n

文本

\n
\n
可选
\n
\n
\n
\n\nimage\n\nstring\n
\n

图片url或base64，最大支持10mb，支持的图片格式jpg、jpeg、png、bmp

\n
\n
可选
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n\nuser\n\nstring\n
\n

表示最终用户的唯一标识符

\n
\n
可选
\n
\n
\n
\n\nencoding_format\n\nstring\n
\n

当前只支持float

\n
\n
可选
\n
\n
\n
\n
\n
\n
\n
\n
\n
请求结构
\n\n
\n
\n\n
\n
POST /v2/embeddings HTTP/1.1\nHost: qianfan.baidubce.com\nAuthorization: authorization string\n{\n   \"model\": \"embedding-v1\" \n   \"input\":[\"White T-shirt\"]\n   \n}
\n
\n
\n
\n
\n
\n
\n
\n

示例代码

\n
\n
\n\n\n
\n
\n
\n
\n\n
\n
\n
\n
\n\n\n
\n
\n\n
\n
\n\n
\n
curl --location 'https://qianfan.baidubce.com/v2/embeddings' \\\n--header 'Content-Type: application/json' \\\n--header 'Authorization: Bearer bce-v3/ALTAK-*********/614fb**********' \\\n--data '{\n    \"model\": \"embedding-v1\",\n    \"input\":[\"White T-shirt\"]\n}'
\n
\n\n
\n
import requests\nimport json\n\ndef main():\n    url = \"https://qianfan.baidubce.com/v2/embeddings\"\n    \n    payload = json.dumps({\n        \"model\": \"embedding-v1\",\n        \"input\":[\"White T-shirt\"]\n    })\n    headers = {\n        'Content-Type': 'application/json',\n        'Authorization': 'Bearer bce-v3/ALTAK-*********/614fb**********'\n    }\n    \n    response = requests.request(\"POST\", url, headers=headers, data=payload)\n    \n    print(response.text)\n    \n\nif __name__ == '__main__':\n    main()
\n
\n
\n
\n
\n\n
\n
\n
\n
\n\n\n
\n
\n\n
\n
\n\n
\n
curl --location 'https://qianfan.baidubce.com/v2/embeddings' \\\n--header 'Content-Type: application/json' \\\n--header 'Authorization: Bearer bce-v3/ALTAK-*********/614fb**********' \\\n--data '{\n    \"model\": \"gme-qwen2-vl-2b-instruct\",\n    \"input\": [\n        {\n            \"text\": \"这个职业在国内的前景怎样？⽬前国内好像没有这个职业？Quant 这个职业在国内的前景怎样？⽬前国内好像没有这个职业？\",\n            \"image\": \"https://i-blo******fa8a3.png\"\n        }\n    ]\n}'
\n
\n\n
\n
import requests\nimport json\n\ndef main():\n    url = \"https://qianfan.baidubce.com/v2/embeddings\"\n    \n    payload = json.dumps({\n        \"model\": \"gme-qwen2-vl-2b-instruct\",\n        \"input\": [\n        {\n            \"text\": \"这个职业在国内的前景怎样？⽬前国内好像没有这个职业？Quant 这个职业在国内的前景怎样？⽬前国内好像没有这个职业？\",\n            \"image\": \"https://i-blo******fa8a3.png\"\n        }\n        ]\n    })\n    headers = {\n        'Content-Type': 'application/json',\n        'Authorization': 'Bearer bce-v3/ALTAK-*********/614fb**********'\n    }\n    \n    response = requests.request(\"POST\", url, headers=headers, data=payload)\n    \n    print(response.text)\n    \n\nif __name__ == '__main__':\n    main()
\n
\n
\n
\n
\n
\n
\n
\n

返回响应

\n
\n
\n
\n
\n
Headers 参数
\n
除公共头域外，无其它特殊头域
\n
\n
\n
\n
\n
返回参数
\n
\n
\n
\n
\n
\n\nmodel\n\nstring\n
\n

模型ID

\n
\n
可选
\n
\n
\n
\n\nid\n\nstring\n
\n

本轮对话的id

\n
\n
可选
\n
\n
\n
\n\nobject\n\nstring\n
\n

回包类型“list”

\n
\n
可选
\n
\n
\n
\n\ncreated\n\ninteger\n
\n

时间戳

\n
\n
可选
\n
\n
\n
\n\ndata\n\narray\n
\n

embedding信息，data成员数和文本数量保持一致

\n
\n
可选
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\nitems\n\nobject {3}\n
\n

embedding信息

\n
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\nobject\n\nstring\n
\n

固定值embedding

\n
\n
可选
\n
\n
\n
\n\nembedding\n\narray\n
\n

embedding 内容

\n
\n
可选
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\nitems\n\nnumber\n
\n
\n
\n
\n
\n
\n
\n
\n\nindex\n\ninteger\n
\n

序号

\n
\n
可选
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n\nusage\n\nobject {4}\n
\n

token统计信息

\n
\n
可选
\n
\n\n
\n\n显示子属性\n隐藏子属性\n
\n\n
\n
\n
\n\nprompt_tokens\n\ninteger\n
\n

问题tokens数（包含历史QA）

\n
\n
可选
\n
\n
\n
\n\nprompt_tokens_details\n\ninteger\n
\n

问题token详情，说明：当调用对话Chat API返回此参数

\n
\n
可选
\n
\n
\n
\n\ncompletion_tokens\n\ninteger\n
\n

回答tokens数，说明：当调用对话Chat API返回此参数

\n
\n
可选
\n
\n
\n
\n\ntotal_tokens\n\ninteger\n
\n

总tokens数

\n
\n
可选
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n\n
\n
\n
\n
响应示例
\n\n
\n
\n\n
\n
{\n    \"id\": \"as-xz2r36ena8\",\n    \"object\": \"list\",\n    \"created\": 1737030777,\n    \"data\": [\n        {\n            \"object\": \"embedding\",\n            \"embedding\": [\n                0.018346669152379036,\n                0.009424751624464989,\n                -0.009573426097631454,\n                ...,\n                -0.3628600239753723\n            ],\n            \"index\": 0\n        }\n    ],\n    \"model\": \"embedding-v1\",\n    \"usage\": {\n        \"prompt_tokens\": 3,\n        \"total_tokens\": 3\n    }\n}
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n

错误码

\n

如果请求错误，服务器返回的JSON文本包含以下参数。

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
名称描述
code错误码
message错误描述信息，帮助理解和解决发生的错误
type错误类型
\n

更多相关错误码，请查看模型错误码说明。

\n
\n
","fields":{"slug":"vmh8u2gsu","title":"向量","date":"2025-11-04","extractedHeadings":[{"value":"支持模型列表","depth":2},{"value":"注意事项","depth":2},{"value":"权限说明","depth":2},{"value":"请求参数","depth":2},{"value":"示例代码","depth":2},{"value":"返回响应","depth":2},{"value":"错误码","depth":2}]},"headings":[]}},"pageContext":{"isCreatedByStatefulCreatePages":false,"slug":"vmh8u2gsu","prev":{"id":"8mh8u2grn","name":"图像编辑","path":"8mh8u2grn","filePath":"大模型服务/图像编辑.md","seo":null,"parentIds":["kmh8tve4a"],"parents":[{"id":"kmh8tve4a","documentId":"cf6404b4-58de-4059-8924-7128c6b0e581","name":"大模型服务","repoName":"aigallery","filePath":"大模型服务","disabled":false,"path":"kmh8tve4a","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":{"title":null,"keywords":null,"description":null,"serviceType":null},"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":""}]},"next":{"id":"xmh8u2gu6","name":"重排序","path":"xmh8u2gu6","filePath":"大模型服务/重排序.md","seo":null,"parentIds":["kmh8tve4a"],"parents":[{"id":"kmh8tve4a","documentId":"cf6404b4-58de-4059-8924-7128c6b0e581","name":"大模型服务","repoName":"aigallery","filePath":"大模型服务","disabled":false,"path":"kmh8tve4a","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":{"title":null,"keywords":null,"description":null,"serviceType":null},"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":""}]},"parents":[{"id":"kmh8tve4a","documentId":"cf6404b4-58de-4059-8924-7128c6b0e581","name":"大模型服务","repoName":"aigallery","filePath":"大模型服务","disabled":false,"path":"kmh8tve4a","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":{"title":null,"keywords":null,"description":null,"serviceType":null},"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":""}],"specificSeo":null}}}