{"componentChunkName":"component---src-templates-acg-portal-new-template-tsx","path":"/9mwbl4ta8","result":{"data":{"markdownRemark":{"html":"\n
\n
\n
\n
\n
POST
\n
\nhttp://{host}/v{version}/row?search\n
\n
\n
\n

基于向量相似性进行查询检索

\n
\n
\n

权限说明

\n

鉴权认证机制的详细内容请参见鉴权认证

\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
URL 参数
\n
\n
\n
\n
\n
\n\nversion\n\nstring\n
\n

API版本号，当前取1。

\n
\n
必选
\n
\n
\n
\n\nhost\n\nstring\n
\n

\"{实例IP}:{实例Port}\"

\n
\n
必选
\n
\n
\n
\n
\n
\n
\n
Body 参数
\n
\n
\n
\n
\n
\n\ndatabase\n\nstring\n
\n

指定库的名称。

\n
\n
必选
\n
\n
\n
\n\ntable\n\nstring\n
\n

指定表的名称。

\n
\n
必选
\n
\n
\n
\n\nanns\n\nobject {4}\n
\n

检索请求参数详情。

\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\nvectorField\n\nstring\n
\n

检索的向量字段。

\n
\n
必选
\n
\n
\n
\n\nvector\n\nanyOf {3}\n

多选一，只需要符合下列任意一组子节点

\n
\n

检索的向量数据。支持稠密型向量(List Float)、稀疏性向量(List Array)、二进制向量(String)

\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\nvector\n\narray\n
\n

稠密向量

\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\nfloat\n
\n
\n
\n
\n
\n
\n
\n
\n\nvector\n\narray\n
\n

稀疏向量

\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\narray\n
\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\nfloat\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n\nvector\n\nstring\n
\n

二进制向量

\n
\n
\n
\n
\n
\n
\n
\n\nparams\n\nobject {6}\n
\n

向量检索参数详情。

\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\nM\n\ninteger\n
\n

HNSW、HNSWPQ索引算法参数，取值范围为[4, 128]。该参数表示每个节点在索引构图中可以连接多少个邻居节点。

\n
\n
可选
\n
\n
\n
\n\nefConstruction\n\ninteger\n
\n

HNSW、HNSWPQ索引算法参数，取值范围为[8, 1024]。该参数表示搜索时指定寻找节点邻居遍历的范围。数值越大构图效果越好，构图时间也越长。

\n
\n
可选
\n
\n
\n
\n\nNSQ\n\ninteger\n
\n

HNSWPQ索引参数，取值范围为[1, dim]。该参数表示量化子空间个数，pq量化相关系数，要求NSQ | dim，NSQ越大量化越精细

\n
\n
可选
\n
\n
\n
\n\nsampleRate\n\nfloat\n
\n

HNSWPQ索引参数，取值范围为[0.0f, 1.0f]。该参数表示kmeans的采样率，pq抽样总数：10000 + (rowCount - 10000)*sampleRate

\n
\n
可选
\n
\n
\n
\n\nfineClusterCount\n\ninteger\n
\n

PUCK索引算法参数，取值范围为[1, 5000]。该参数表示每个粗聚类中心下细聚类中心个数。

\n
\n
可选
\n
\n
\n
\n\ncoarseClusterCount\n\ninteger\n
\n

PUCK索引算法参数，取值范围为[1, 5000]。该参数表示索引中粗聚类中心个数。

\n
\n
可选
\n
\n
\n
\n
\n
\n
\n\nfilter\n\nstring\n
\n

过滤条件

\n
\n
可选
\n
\n
\n
\n
\n
\n
\n\npartitionKey\n\nobject {0}\n
\n

需要注意的是，如果没有指定分区键值，那么该检索请求可能会退化为在该表所有分片上都执行的MPP检索。

\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
\n
\n
\n\nprojections\n\narray\n
\n

指定返回的字段列表，不指定则返回全部字段。

\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\nstring\n
\n
\n
\n
\n
\n
\n
\n
\n\nreadConsistency\n\nstring\n
\n

查询请求的一致性级别，取值为：

  • EVENTUAL（默认值）：最终一致性，查询请求会随机发送给分片的所有副本；
  • STRONG：强一致性，查询请求只会发送给分片主副本。

    \n
    • \n
    可选
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    请求结构
    \n\n
    \n
    \n\n
    \n
    POST /v{version}/row?search HTTP/1.1\nHOST: {Endpoint}\nAuthorization: {Authorization}\n{\n    \"database\": \"db_test\",\n    \"table\": \"table_test\",\n    \"anns\": {\n        \"vectorField\": \"vector_field\",\n        \"vector\": [\n                0.2323234,\n                0.34534545,\n                0.9837234\n        ],\n        \"params\": {\n           \"ef\": 100,\n           \"limit\": 10\n        },\n        \"filter\": \"id != '00000' AND age < 35\"\n    },\n    \"partitionKey\": {\n        \"username\": \"alice\"\n    },\n    \"projections\": [\"id\", \"username\"],\n    \"readConsistency\": \"EVENTUAL\"\n}
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n

    示例代码

    \n
    \n\n
    \n
    \n
    \n
    请求示例
    \n\n
    \n
    \n\n
    \n
    curl --location --request POST 'http://vdb.nXWNyPCOSLci.vdb.bj.baidubce.com/v1/row?search' \\\n--header 'Authorization: Bearer account=root&api_key=eC4bLRy2va******************************' \\\n--header 'Content-Type: application/json' \\\n--data '{\n    \"database\": \"db_test\",\n    \"table\": \"table_test\",\n    \"primaryKey\": {\n        \"id\": \"00001\"\n    },\n    \"partitionKey\": {\n        \"username\": \"alice\"\n    },\n    \"projections\": [\"id\", \"username\", \"vector_field\"],\n    \"retrieveVector\": true,\n    \"readConsistency\": \"EVENTUAL\"\n}'
    \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\nmsg\n\nstring\n
    \n

    返回信息

    \n
    \n
    可选
    \n
    \n
    \n
    \n\ncode\n\ninteger\n
    \n

    返回码

    \n
    \n
    可选
    \n
    \n
    \n
    \n\nrows\n\narray\n
    \n

    检索结果列表

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

    检索结果记录的详情。

    \n
    \n
    可选
    \n
    \n
    \n
    \n\ndistance\n\nfloat\n
    \n

    结果记录与目标向量的距离。说明如下：

  • 在L2距离度量算法下，距离越小，与搜索向量越相似；
  • 在IP和COSINE距离度量算法下，距离越大，与搜索向量越相似。

    \n
    • \n
    可选
    \n
    \n
    \n
    \n\nscore\n\nfloat\n
    \n

    记录得分，得分越高，与搜索向量越相似。

    \n
    \n
    可选
    \n
    \n
    \n
    \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    \"code\": 0,\n    \"msg\": \"Success\",\n    \"rows\": [\n        {\n            \"row\": {\n                \"id\": \"00001\",\n                \"username\": \"alice\",\n                \"vector_field\": [\n                    0.20354213,\n                    0.35934591,\n                    0.89238402\n                ]\n            },\n            \"distance\": 0.01,\n            \"score\": 1.0\n        },\n        {\n            \"row\": {\n                \"id\": \"00002\",\n                \"username\": \"bob\",\n                \"vector_field\": [\n                    0.21354213,\n                    0.34934591,\n                    0.90238402\n                ]\n            },\n            \"distance\": 0.05,\n            \"score\": 0.99\n        }\n    ]\n}
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    \n
    ","fields":{"slug":"9mwbl4ta8","title":"向量检索","date":"2026-11-11","extractedHeadings":[{"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}]},"headings":[]}},"pageContext":{"isCreatedByStatefulCreatePages":false,"slug":"9mwbl4ta8","prev":{"id":"jmwbl4t8v","name":"回收用户的角色","path":"jmwbl4t8v","filePath":"Agent/向量数据库/数据面/回收用户的角色.md","seo":null,"parentIds":["Mmwbl4qxa","Gmwbl4soa","Umwbl4soi"],"parents":[{"id":"Mmwbl4qxa","documentId":"14a689a9-e16b-4e40-ba67-9e0a3a66f51e","name":"Agent","repoName":"qianfan-api","filePath":"Agent","disabled":false,"path":"Mmwbl4qxa","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null},{"id":"Gmwbl4soa","documentId":"1874b1d0-8471-4bdd-a0f6-bef63d790cd0","name":"向量数据库","repoName":"qianfan-api","filePath":"Agent/向量数据库","disabled":false,"path":"Gmwbl4soa","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null},{"id":"Umwbl4soi","documentId":"46e45008-14d8-4534-bdce-d35677fcd313","name":"数据面","repoName":"qianfan-api","filePath":"Agent/向量数据库/数据面","disabled":false,"path":"Umwbl4soi","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null}]},"next":{"id":"Bmwbl4tbu","name":"列出所有表","path":"Bmwbl4tbu","filePath":"Agent/向量数据库/数据面/列出所有表.md","seo":null,"parentIds":["Mmwbl4qxa","Gmwbl4soa","Umwbl4soi"],"parents":[{"id":"Mmwbl4qxa","documentId":"14a689a9-e16b-4e40-ba67-9e0a3a66f51e","name":"Agent","repoName":"qianfan-api","filePath":"Agent","disabled":false,"path":"Mmwbl4qxa","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null},{"id":"Gmwbl4soa","documentId":"1874b1d0-8471-4bdd-a0f6-bef63d790cd0","name":"向量数据库","repoName":"qianfan-api","filePath":"Agent/向量数据库","disabled":false,"path":"Gmwbl4soa","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null},{"id":"Umwbl4soi","documentId":"46e45008-14d8-4534-bdce-d35677fcd313","name":"数据面","repoName":"qianfan-api","filePath":"Agent/向量数据库/数据面","disabled":false,"path":"Umwbl4soi","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null}]},"parents":[{"id":"Mmwbl4qxa","documentId":"14a689a9-e16b-4e40-ba67-9e0a3a66f51e","name":"Agent","repoName":"qianfan-api","filePath":"Agent","disabled":false,"path":"Mmwbl4qxa","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null},{"id":"Gmwbl4soa","documentId":"1874b1d0-8471-4bdd-a0f6-bef63d790cd0","name":"向量数据库","repoName":"qianfan-api","filePath":"Agent/向量数据库","disabled":false,"path":"Gmwbl4soa","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null},{"id":"Umwbl4soi","documentId":"46e45008-14d8-4534-bdce-d35677fcd313","name":"数据面","repoName":"qianfan-api","filePath":"Agent/向量数据库/数据面","disabled":false,"path":"Umwbl4soi","lastMergeTime":null,"isApiDoc":null,"httpMethod":null,"seo":null,"sourceOrgName":null,"sourceRepoName":null,"sourceDocumentId":"","solutionTag":null,"solutionColor":null}],"specificSeo":null}}}