Query
除了 ANN 搜索外,Milvus 还支持通过查询进行元数据过滤。本页介绍如何使用 Query、Get 和 QueryIterator 来进行元数据过滤。
概述
Collection 可以存储各种类型的标量 field。您可以让 Milvus 基于一个或多个标量 field 过滤 Entity。Milvus 提供三种类型的查询:Query、Get 和 QueryIterator。下表比较了这三种查询类型。
Get | Query | QueryIterator | |
---|---|---|---|
适用场景 | 查找具有指定 primary key 的 entity。 | 查找满足自定义过滤条件的所有或指定数量的 entity | 通过分页查询查找满足自定义过滤条件的所有 entity。 |
过滤方法 | 按 primary key | 按过滤表达式。 | 按过滤表达式。 |
必需参数 |
|
|
|
可选参数 |
|
|
|
返回 | 返回指定 collection 或 partition 中具有指定 primary key 的 entity。 | 返回指定 collection 或 partition 中满足自定义过滤条件的所有或指定数量的 entity。 | 通过分页查询返回指定 collection 或 partition 中满足自定义过滤条件的所有 entity。 |
有关元数据过滤的更多信息,请参阅 Filtering。
使用 Get
当您需要按 primary key 查找 entity 时,可以使用 Get 方法。以下代码示例假设您的 collection 中有名为 id
、vector
和 color
的三个 field,并返回 primary key 为 1
、2
和 3
的 entity。
[
{"id": 0, "vector": [0.3580376395471989, -0.6023495712049978, 0.18414012509913835, -0.26286205330961354, 0.9029438446296592], "color": "pink_8682"},
{"id": 1, "vector": [0.19886812562848388, 0.06023560599112088, 0.6976963061752597, 0.2614474506242501, 0.838729485096104], "color": "red_7025"},
{"id": 2, "vector": [0.43742130801983836, -0.5597502546264526, 0.6457887650909682, 0.7894058910881185, 0.20785793220625592], "color": "orange_6781"},
{"id": 3, "vector": [0.3172005263489739, 0.9719044792798428, -0.36981146090600725, -0.4860894583077995, 0.95791889146345], "color": "pink_9298"},
{"id": 4, "vector": [0.4452349528804562, -0.8757026943054742, 0.8220779437047674, 0.46406290649483184, 0.30337481143159106], "color": "red_4794"},
{"id": 5, "vector": [0.985825131989184, -0.8144651566660419, 0.6299267002202009, 0.1206906911183383, -0.1446277761879955], "color": "yellow_4222"},
{"id": 6, "vector": [0.8371977790571115, -0.015764369584852833, -0.31062937026679327, -0.562666951622192, -0.8984947637863987], "color": "red_9392"},
{"id": 7, "vector": [-0.33445148015177995, -0.2567135004164067, 0.8987539745369246, 0.9402995886420709, 0.5378064918413052], "color": "grey_8510"},
{"id": 8, "vector": [0.39524717779832685, 0.4000257286739164, -0.5890507376891594, -0.8650502298996872, -0.6140360785406336], "color": "white_9381"},
{"id": 9, "vector": [0.5718280481994695, 0.24070317428066512, -0.3737913482606834, -0.06726932177492717, -0.6980531615588608], "color": "purple_4976"},
]
您可以按以下方式通过 ID 获取 entity。
from pymilvus import MilvusClient
client = MilvusClient(
uri="http://localhost:19530",
token="root:Milvus"
)
res = client.get(
collection_name="my_collection",
ids=[0, 1, 2],
output_fields=["vector", "color"]
)
print(res)
import io.milvus.v2.client.ConnectConfig;
import io.milvus.v2.client.MilvusClientV2;
import io.milvus.v2.service.vector.request.GetReq
import io.milvus.v2.service.vector.request.GetResp
import java.util.*;
MilvusClientV2 client = new MilvusClientV2(ConnectConfig.builder()
.uri("http://localhost:19530")
.token("root:Milvus")
.build());
GetReq getReq = GetReq.builder()
.collectionName("my_collection")
.ids(Arrays.asList(0, 1, 2))
.outputFields(Arrays.asList("vector", "color"))
.build();
GetResp getResp = client.get(getReq);
List<QueryResp.QueryResult> results = getResp.getGetResults();
for (QueryResp.QueryResult result : results) {
System.out.println(result.getEntity());
}
// Output
// {color=pink_8682, vector=[0.35803765, -0.6023496, 0.18414013, -0.26286206, 0.90294385], id=0}
// {color=red_7025, vector=[0.19886813, 0.060235605, 0.6976963, 0.26144746, 0.8387295], id=1}
// {color=orange_6781, vector=[0.43742132, -0.55975026, 0.6457888, 0.7894059, 0.20785794], id=2}
import (
"context"
"fmt"
"github.com/milvus-io/milvus/client/v2/column"
"github.com/milvus-io/milvus/client/v2/entity"
"github.com/milvus-io/milvus/client/v2/milvusclient"
)
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
milvusAddr := "localhost:19530"
client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
Address: milvusAddr,
})
if err != nil {
fmt.Println(err.Error())
// handle error
}
defer client.Close(ctx)
resultSet, err := client.Get(ctx, milvusclient.NewQueryOption("my_collection").
WithConsistencyLevel(entity.ClStrong).
WithIDs(column.NewColumnInt64("id", []int64{0, 1, 2})).
WithOutputFields("vector", "color"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
fmt.Println("id: ", resultSet.GetColumn("id").FieldData().GetScalars())
fmt.Println("vector: ", resultSet.GetColumn("vector").FieldData().GetVectors())
fmt.Println("color: ", resultSet.GetColumn("color").FieldData().GetScalars())
import { MilvusClient, DataType } from "@zilliz/milvus2-sdk-node";
const address = "http://localhost:19530";
const token = "root:Milvus";
const client = new MilvusClient({address, token});
const res = client.get({
collection_name: "my_collection",
ids: [0,1,2],
output_fields: ["vector", "color"]
})
export CLUSTER_ENDPOINT="http://localhost:19530"
export TOKEN="root:Milvus"
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/get" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"id": [0, 1, 2],
"outputFields": ["vector", "color"]
}'
# {"code":0,"cost":0,"data":[{"color":"pink_8682","id":0,"vector":[0.35803765,-0.6023496,0.18414013,-0.26286206,0.90294385]},{"color":"red_7025","id":1,"vector":[0.19886813,0.060235605,0.6976963,0.26144746,0.8387295]},{"color":"orange_6781","id":2,"vector":[0.43742132,-0.55975026,0.6457888,0.7894059,0.20785794]}]}
使用 Query
当您需要按自定义过滤条件查找 entity 时,请使用 Query 方法。以下代码示例假设有三个名为 id
、vector
和 color
的 field,并返回持有以 red
开头的 color
值的指定数量的 entity。
from pymilvus import MilvusClient
client = MilvusClient(
uri="http://localhost:19530",
token="root:Milvus"
)
res = client.query(
collection_name="my_collection",
filter="color like \"red%\"",
output_fields=["vector", "color"],
limit=3
)
import io.milvus.v2.service.vector.request.QueryReq
import io.milvus.v2.service.vector.request.QueryResp
QueryReq queryReq = QueryReq.builder()
.collectionName("my_collection")
.filter("color like \"red%\"")
.outputFields(Arrays.asList("vector", "color"))
.limit(3)
.build();
QueryResp getResp = client.query(queryReq);
List<QueryResp.QueryResult> results = getResp.getQueryResults();
for (QueryResp.QueryResult result : results) {
System.out.println(result.getEntity());
}
// Output
// {color=red_7025, vector=[0.19886813, 0.060235605, 0.6976963, 0.26144746, 0.8387295], id=1}
// {color=red_4794, vector=[0.44523495, -0.8757027, 0.82207793, 0.4640629, 0.3033748], id=4}
// {color=red_9392, vector=[0.8371978, -0.015764369, -0.31062937, -0.56266695, -0.8984948], id=6}
import (
"context"
"fmt"
"github.com/milvus-io/milvus/client/v2/column"
"github.com/milvus-io/milvus/client/v2/entity"
"github.com/milvus-io/milvus/client/v2/milvusclient"
)
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
milvusAddr := "localhost:19530"
client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
Address: milvusAddr,
})
if err != nil {
fmt.Println(err.Error())
// handle error
}
defer client.Close(ctx)
resultSet, err := client.Query(ctx, milvusclient.NewQueryOption("my_collection").
WithFilter("color like \"red%\"").
WithOutputFields("vector", "color"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
fmt.Println("id: ", resultSet.GetColumn("id").FieldData().GetScalars())
fmt.Println("vector: ", resultSet.GetColumn("vector").FieldData().GetVectors())
fmt.Println("color: ", resultSet.GetColumn("color").FieldData().GetScalars())
import { MilvusClient, DataType } from "@zilliz/milvus2-sdk-node";
const address = "http://localhost:19530";
const token = "root:Milvus";
const client = new MilvusClient({address, token});
const res = client.query({
collection_name: "my_collection",
filter: 'color like "red%"',
output_fields: ["vector", "color"],
limit: 3
})
export CLUSTER_ENDPOINT="http://localhost:19530"
export TOKEN="root:Milvus"
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/query" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"filter": "color like \"red%\"",
"limit": 3,
"outputFields": ["vector", "color"]
}'
#{"code":0,"cost":0,"data":[{"color":"red_7025","id":1,"vector":[0.19886813,0.060235605,0.6976963,0.26144746,0.8387295]},{"color":"red_4794","id":4,"vector":[0.44523495,-0.8757027,0.82207793,0.4640629,0.3033748]},{"color":"red_9392","id":6,"vector":[0.8371978,-0.015764369,-0.31062937,-0.56266695,-0.8984948]}]}
使用 QueryIterator
当您需要通过分页查询来查找满足自定义过滤条件的 entity 时,可以创建一个 QueryIterator 并使用其 next() 方法来迭代所有 entity,以查找满足过滤条件的 entity。以下代码示例假设有三个名为 id
、vector
和 color
的 field,并返回所有持有以 red
开头的 color
值的 entity。
from pymilvus import connections, Collection
connections.connect(
uri="http://localhost:19530",
token="root:Milvus"
)
collection = Collection("my_collection")
iterator = collection.query_iterator(
batch_size=10,
expr="color like \"red%\"",
output_fields=["color"]
)
results = []
while True:
result = iterator.next()
if not result:
iterator.close()
break
print(result)
results += result
import io.milvus.orm.iterator.QueryIterator;
import io.milvus.response.QueryResultsWrapper;
import io.milvus.v2.common.ConsistencyLevel;
import io.milvus.v2.service.vector.request.QueryIteratorReq;
QueryIteratorReq req = QueryIteratorReq.builder()
.collectionName("my_collection")
.expr("color like \"red%\"")
.batchSize(50L)
.outputFields(Collections.singletonList("color"))
.consistencyLevel(ConsistencyLevel.BOUNDED)
.build();
QueryIterator queryIterator = client.queryIterator(req);
while (true) {
List<QueryResultsWrapper.RowRecord> res = queryIterator.next();
if (res.isEmpty()) {
queryIterator.close();
break;
}
for (QueryResultsWrapper.RowRecord record : res) {
System.out.println(record);
}
}
// Output
// [color:red_7025, id:1]
// [color:red_4794, id:4]
// [color:red_9392, id:6]
// go
import { MilvusClient, DataType } from "@zilliz/milvus2-sdk-node";
const iterator = await milvusClient.queryIterator({
collection_name: 'my_collection',
batchSize: 10,
expr: 'color like "red%"',
output_fields: ['color'],
});
const results = [];
for await (const value of iterator) {
results.push(...value);
page += 1;
}
# Not available
Partition 中的查询
您也可以通过在 Get、Query 或 QueryIterator 请求中包含 partition 名称来在一个或多个 partition 内执行查询。以下代码示例假设 collection 中有一个名为 PartitionA 的 partition。
from pymilvus import MilvusClient
client = MilvusClient(
uri="http://localhost:19530",
token="root:Milvus"
)
res = client.get(
collection_name="my_collection",
partitionNames=["partitionA"],
ids=[10, 11, 12],
output_fields=["vector", "color"]
)
from pymilvus import MilvusClient
client = MilvusClient(
uri="http://localhost:19530",
token="root:Milvus"
)
res = client.query(
collection_name="my_collection",
partitionNames=["partitionA"],
filter="color like \"red%\"",
output_fields=["vector", "color"],
limit=3
)
# Use QueryIterator
from pymilvus import connections, Collection
connections.connect(
uri="http://localhost:19530",
token="root:Milvus"
)
collection = Collection("my_collection")
iterator = collection.query_iterator(
partition_names=["partitionA"],
batch_size=10,
expr="color like \"red%\"",
output_fields=["color"]
)
results = []
while True:
result = iterator.next()
if not result:
iterator.close()
break
print(result)
results += result
GetReq getReq = GetReq.builder()
.collectionName("my_collection")
.partitionName("partitionA")
.ids(Arrays.asList(10, 11, 12))
.outputFields(Collections.singletonList("color"))
.build();
GetResp getResp = client.get(getReq);
QueryReq queryReq = QueryReq.builder()
.collectionName("my_collection")
.partitionNames(Collections.singletonList("partitionA"))
.filter("color like \"red%\"")
.outputFields(Collections.singletonList("color"))
.limit(3)
.build();
QueryResp getResp = client.query(queryReq);
QueryIteratorReq req = QueryIteratorReq.builder()
.collectionName("my_collection")
.partitionNames(Collections.singletonList("partitionA"))
.expr("color like \"red%\"")
.batchSize(50L)
.outputFields(Collections.singletonList("color"))
.consistencyLevel(ConsistencyLevel.BOUNDED)
.build();
QueryIterator queryIterator = client.queryIterator(req);
resultSet, err := client.Get(ctx, milvusclient.NewQueryOption("my_collection").
WithPartitions("partitionA").
WithIDs(column.NewColumnInt64("id", []int64{10, 11, 12})).
WithOutputFields("vector", "color"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
fmt.Println("id: ", resultSet.GetColumn("id").FieldData().GetScalars())
fmt.Println("vector: ", resultSet.GetColumn("vector").FieldData().GetVectors())
fmt.Println("color: ", resultSet.GetColumn("color").FieldData().GetScalars())
resultSet, err := client.Query(ctx, milvusclient.NewQueryOption("my_collection").
WithPartitions("partitionA").
WithFilter("color like \"red%\"").
WithOutputFields("vector", "color"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
fmt.Println("id: ", resultSet.GetColumn("id").FieldData().GetScalars())
fmt.Println("vector: ", resultSet.GetColumn("vector").FieldData().GetVectors())
fmt.Println("color: ", resultSet.GetColumn("color").FieldData().GetScalars())
import { MilvusClient, DataType } from "@zilliz/milvus2-sdk-node";
const address = "http://localhost:19530";
const token = "root:Milvus";
const client = new MilvusClient({address, token});
// Use get
var res = client.query({
collection_name: "my_collection",
partition_names: ["partitionA"],
filter: 'color like "red%"',
output_fields: ["vector", "color"],
limit: 3
})
// Use query
res = client.query({
collection_name: "my_collection",
partition_names: ["partitionA"],
filter: "color like \"red%\"",
output_fields: ["vector", "color"],
limit: 3
})
// Use queryiterator
const iterator = await milvusClient.queryIterator({
collection_name: 'my_collection',
partition_names: ['partitionA'],
batchSize: 10,
expr: 'color like "red%"',
output_fields: ['color'],
});
const results = [];
for await (const value of iterator) {
results.push(...value);
page += 1;
}
export CLUSTER_ENDPOINT="http://localhost:19530"
export TOKEN="root:Milvus"
# Use get
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/get" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"partitionNames": ["partitionA"],
"id": [0, 1, 2],
"outputFields": ["vector", "color"]
}'
# Use query
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/get" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"partitionNames": ["partitionA"],
"filter": "color like \"red%\"",
"limit": 3,
"outputFields": ["vector", "color"],
"id": [0, 1, 2]
}'