50 lines
1.8 KiB
Markdown
50 lines
1.8 KiB
Markdown
## 背景
|
||
|
||
向量检索是指用一组数字(向量)来量化一个事物，用大量向量来表示事物集合，用向量计算的方式寻找相似事物的一种检索方式。
|
||
|
||
isearch底层采用的向量检索框架为Facebook AI的Faiss，项目地址为：https://github.com/facebookresearch/faiss
|
||
|
||
## app_field_define表
|
||
|
||
在app_field_define表定义时，vector字段类型需定义好dim、index_type和metric_type三个属性，示例如下：
|
||
```
|
||
{
|
||
"id":3,
|
||
"appId":10065,
|
||
"fieldName":"float_vector",
|
||
"fieldType":15,
|
||
"fieldId":3,
|
||
"IsPrimaryKey":0,
|
||
"indexTag":0,
|
||
"snapshotTag":1,
|
||
"segmentTag":0,
|
||
"segmentFeature":0,
|
||
"unionField":"",
|
||
"createTime":"2021/4/13 15:49:09",
|
||
"dim":128, // 维数
|
||
"index_type": [" PCA80,Flat "], // 索引类型，格式与faiss对外工厂类设置保持一致
|
||
"metric_type": "L2" // 距离计算方式，可选值：InnerProduct、L2
|
||
}
|
||
|
||
```
|
||
|
||
说明：index_type参考https://github.com/facebookresearch/faiss/wiki/The-index-factory
|
||
|
||
## 向量插入示例
|
||
|
||
```
|
||
curl -X POST \
|
||
http://127.0.0.1/insert \
|
||
-H 'content-type: application/json' \
|
||
-H 'doc_id: 1' \
|
||
-d '{"appid":10065,"table_content":{"cmd":"add","fields":{"doc_id":"1","random_value":1488981884,"float_vector":[0.005653954876242762, 0.632130963117687, 0.7519577013172226, 0.8568273368123129, 0.2034335192251041, 0.9786219451736441, 0.5948105950093241, 0.9618089054657426]}}}'
|
||
```
|
||
|
||
## 向量查询示例
|
||
|
||
```
|
||
curl -X POST \
|
||
http://127.0.0.1/search \
|
||
-H 'content-type: application/json' \
|
||
-d '{"appid":10065,"query":{"vector_query":{"float_vector":[0.005653954876242762, 0.632130963117687, 0.7519577013172226, 0.8568273368123129, 0.2034335192251041, 0.9786219451736441, 0.5948105950093241, 0.9618089054657426], "index_type_id":1}} }'
|
||
``` |