布尔与数值类型
布尔与数值类型的标量字段用于存放布尔值或标量数值。布尔值是指在两个可能的值中取一个,而标量数值则既可能是整数,也可能是小数。它们通常用来表示数量、度量值或其它需要进行逻辑或数学运算的数据。
如下表格描述了 Zilliz Cloud 支持的布尔与数值类数据类型。
数据类型 | 描述 |
---|---|
| 布尔类型,用于存储 |
| 8 位整数,适用于存储小范围的整数数据。 |
| 16 位整数,适用于存储中等范围的整数数据。 |
| 32 位整数,适合一般整型数据存储,如商品数量或用户 ID。 |
| 64 位整数,适合存储较大范围的数据,例如时间戳或标识符。 |
| 32 位浮点数,适用于一般精度的数值数据,如评分或温度。 |
| 64 位双精度浮点数,适用于需要高精度的数据,如金融数据或科学计算。 |
如需定义一个布尔类型的字段,需要将 datatype
设置成 BOOL
。如需定义一个数值类型的字段,则可以将 datatype
设置成上述支持的数值类型。例如,DataType.INT64
表示一个整数类型的字段,而 DataType.FLOAT
则表示一个小数类型的字段。
Zilliz Cloud 允许布尔类型或数值类型的字段为空。您也可以为它们设置默认值。简单来说,您可以将字段的 nullable
设置为 True
来允许字段为空,并通过 default_value
为字段设置默认值,具体可以参考 Nullable 和默认值。
添加布尔或数值字段
您可以在 Collection Schema 中字义布尔或数值类型的字段来存放相应类型的数据。在下方的示例中,Schema 中定义了如下字段:
-
age
:用于存放整数类型的数据,允许为空,默认值为18
。 -
broken
:用于存放布尔类型的数据,允许为空,无默认值。 -
height
:用于存放小数类型的数据,允许为空,无默认值。
如果您在定义 Schema 时将 enabled_dynamic_fields
设置为 True
,您还可以在该 Collection 中插入 Schema 中未定义的字段。此操作可能会增加查询和管理的复杂性,并影响查询性能。更多详情,请参考 Dynamic Field。
- Python
- Java
- NodeJS
- Go
- cURL
# Import necessary libraries
from pymilvus import MilvusClient, DataType
# Define server address
SERVER_ADDR = "YOUR_CLUSTER_ENDPOINT"
# Create a MilvusClient instance
client = MilvusClient(uri=SERVER_ADDR)
# Define the collection schema
schema = client.create_schema(
auto_id=False,
enable_dynamic_fields=True,
)
# Add an INT64 field `age` that supports null values with default value 18
schema.add_field(field_name="age", datatype=DataType.INT64, nullable=True, default_value=18)
schema.add_field(field_name="broken", datatype=DataType.BOOL, nullable=True)
# Add a FLOAT field `price` that supports null values without default value
schema.add_field(field_name="price", datatype=DataType.FLOAT, nullable=True)
schema.add_field(field_name="pk", datatype=DataType.INT64, is_primary=True)
schema.add_field(field_name="embedding", datatype=DataType.FLOAT_VECTOR, dim=3)
import io.milvus.v2.client.ConnectConfig;
import io.milvus.v2.client.MilvusClientV2;
import io.milvus.v2.common.DataType;
import io.milvus.v2.service.collection.request.AddFieldReq;
import io.milvus.v2.service.collection.request.CreateCollectionReq;
MilvusClientV2 client = new MilvusClientV2(ConnectConfig.builder()
.uri("YOUR_CLUSTER_ENDPOINT")
.build());
CreateCollectionReq.CollectionSchema schema = client.createSchema();
schema.setEnableDynamicField(true);
schema.addField(AddFieldReq.builder()
.fieldName("age")
.dataType(DataType.Int64)
.isNullable(true)
.defaultValue(18)
.build());
schema.addField(AddFieldReq.builder()
.fieldName("broken")
.dataType(DataType.BOOL)
.isNullable(true)
.build());
schema.addField(AddFieldReq.builder()
.fieldName("price")
.dataType(DataType.Float)
.isNullable(true)
.build());
schema.addField(AddFieldReq.builder()
.fieldName("pk")
.dataType(DataType.Int64)
.isPrimaryKey(true)
.build());
schema.addField(AddFieldReq.builder()
.fieldName("embedding")
.dataType(DataType.FloatVector)
.dimension(3)
.build());
import { MilvusClient, DataType } from "@zilliz/milvus2-sdk-node";
const schema = [
{
name: "age",
data_type: DataType.Int64,
},
{
name: "broken",
data_type: DataType.Bool,
},
{
name: "price",
data_type: DataType.Float,
},
{
name: "pk",
data_type: DataType.Int64,
is_primary_key: true,
},
{
name: "embedding",
data_type: DataType.FloatVector,
dim: 3,
},
];
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/index"
"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)
schema := entity.NewSchema()
schema.WithField(entity.NewField().
WithName("pk").
WithDataType(entity.FieldTypeInt64).
WithIsPrimaryKey(true),
).WithField(entity.NewField().
WithName("embedding").
WithDataType(entity.FieldTypeFloatVector).
WithDim(3),
).WithField(entity.NewField().
WithName("price").
WithDataType(entity.FieldTypeFloat).
WithNullable(true),
).WithField(entity.NewField().
WithName("age").
WithDataType(entity.FieldTypeInt64).
WithNullable(true).
WithDefaultValueLong(18),
).WithField(entity.NewField().
WithName("broken").
WithDataType(entity.FieldTypeBool).
WithNullable(true),
export int64Field='{
"fieldName": "age",
"dataType": "Int64"
}'
export boolField='{
"fieldName": "broken",
"dataType": "Bool"
}'
export floatField='{
"fieldName": "price",
"dataType": "Float"
}'
export pkField='{
"fieldName": "pk",
"dataType": "Int64",
"isPrimary": true
}'
export vectorField='{
"fieldName": "embedding",
"dataType": "FloatVector",
"elementTypeParams": {
"dim": 3
}
}'
export schema="{
\"autoID\": false,
\"fields\": [
$int64Field,
$boolField,
$floatField,
$pkField,
$vectorField
]
}"
设置索引参数
为标量数值字段设置索引参数可以提供查询和搜索效率。在 Zilliz Cloud clusters 中,为向量字段创建索引为必选操作。对于包括布尔和数值类型的标量字段而言,该操作为可选。
以下示例中,我们为向量字段 embedding
和 标量字段 age
创建了 AUTOINDEX
类型的索引,表示 Milvus 会自动根据数据类型创建合适的索引。有关更多信息,请参考 AUTOINDEX。
- Python
- Java
- NodeJS
- Go
- cURL
# Set index params
index_params = client.prepare_index_params()
# Index `age` with AUTOINDEX
index_params.add_index(
field_name="age",
index_type="AUTOINDEX",
index_name="age_index"
)
# Index `embedding` with AUTOINDEX and specify similarity metric type
index_params.add_index(
field_name="embedding",
index_type="AUTOINDEX", # Use automatic indexing to simplify complex index settings
metric_type="COSINE" # Specify similarity metric type, options include L2, COSINE, or IP
)
import io.milvus.v2.common.IndexParam;
import java.util.*;
List<IndexParam> indexes = new ArrayList<>();
indexes.add(IndexParam.builder()
.fieldName("age")
.indexType(IndexParam.IndexType.AUTOINDEX)
.build());
indexes.add(IndexParam.builder()
.fieldName("embedding")
.indexType(IndexParam.IndexType.AUTOINDEX)
.metricType(IndexParam.MetricType.COSINE)
.build());
import { IndexType } from "@zilliz/milvus2-sdk-node";
const indexParams = [
{
field_name: "age",
index_name: "inverted_index",
index_type: IndexType.AUTOINDEX,
},
{
field_name: "embedding",
metric_type: "COSINE",
index_type: IndexType.AUTOINDEX,
},
];
indexOption1 := milvusclient.NewCreateIndexOption("my_collection", "embedding",
index.NewAutoIndex(index.MetricType(entity.IP)))
indexOption2 := milvusclient.NewCreateIndexOption("my_collection", "age",
index.NewInvertedIndex())
export indexParams='[
{
"fieldName": "age",
"indexName": "inverted_index",
"indexType": "AUTOINDEX"
},
{
"fieldName": "embedding",
"metricType": "COSINE",
"indexType": "AUTOINDEX"
}
]'
创建 Collection
定义好 Collection 的 Schema 和索引后,我们便可以创建包含标量字段的 Collection。
- Python
- Java
- NodeJS
- Go
- cURL
# Create Collection
client.create_collection(
collection_name="my_collection",
schema=schema,
index_params=index_params
)
CreateCollectionReq requestCreate = CreateCollectionReq.builder()
.collectionName("my_collection")
.collectionSchema(schema)
.indexParams(indexes)
.build();
client.createCollection(requestCreate);
client.create_collection({
collection_name: "my_collection",
schema: schema,
index_params: indexParams
})
err = client.CreateCollection(ctx,
milvusclient.NewCreateCollectionOption("my_collection", schema).
WithIndexOptions(indexOption1, indexOption2))
if err != nil {
fmt.Println(err.Error())
// handle error
}
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/collections/create" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d "{
\"collectionName\": \"my_collection\",
\"schema\": $schema,
\"indexParams\": $indexParams
}"
插入数据
Collection 创建完成后,可以插入包含标量字段的数据。
- Python
- Java
- NodeJS
- Go
- cURL
# Sample data
data = [
{"age": 25, "price": 99.99, "pk": 1, "embedding": [0.1, 0.2, 0.3]},
{"age": 30, "pk": 2, "embedding": [0.4, 0.5, 0.6]}, # `price` field is missing, which should be null
{"age": None, "price": None, "pk": 3, "embedding": [0.2, 0.3, 0.1]}, # `age` should default to 18, `price` is null
{"age": 45, "price": None, "pk": 4, "embedding": [0.9, 0.1, 0.4]}, # `price` is null
{"age": None, "price": 59.99, "pk": 5, "embedding": [0.8, 0.5, 0.3]}, # `age` should default to 18
{"age": 60, "price": None, "pk": 6, "embedding": [0.1, 0.6, 0.9]} # `price` is null
]
client.insert(
collection_name="my_collection",
data=data
)
import com.google.gson.Gson;
import com.google.gson.JsonObject;
import io.milvus.v2.service.vector.request.InsertReq;
import io.milvus.v2.service.vector.response.InsertResp;
List<JsonObject> rows = new ArrayList<>();
Gson gson = new Gson();
rows.add(gson.fromJson("{\"age\": 25, \"price\": 99.99, \"pk\": 1, \"embedding\": [0.1, 0.2, 0.3]}", JsonObject.class));
rows.add(gson.fromJson("{\"age\": 30, \"pk\": 2, \"embedding\": [0.4, 0.5, 0.6]}", JsonObject.class));
rows.add(gson.fromJson("{\"age\": null, \"price\": null, \"pk\": 3, \"embedding\": [0.2, 0.3, 0.1]}", JsonObject.class));
rows.add(gson.fromJson("{\"age\": 45, \"price\": null, \"pk\": 4, \"embedding\": [0.9, 0.1, 0.4]}", JsonObject.class));
rows.add(gson.fromJson("{\"age\": null, \"price\": 59.99, \"pk\": 5, \"embedding\": [0.8, 0.5, 0.3]}", JsonObject.class));
rows.add(gson.fromJson("{\"age\": 60, \"price\": null, \"pk\": 6, \"embedding\": [0.1, 0.6, 0.9]}", JsonObject.class));
InsertResp insertR = client.insert(InsertReq.builder()
.collectionName("my_collection")
.data(rows)
.build());
const data = [
{ age: 25, price: 99.99, pk: 1, embedding: [0.1, 0.2, 0.3] },
{ age: 30, price: 149.5, pk: 2, embedding: [0.4, 0.5, 0.6] },
{ age: 35, price: 199.99, pk: 3, embedding: [0.7, 0.8, 0.9] },
];
client.insert({
collection_name: "my_collection",
data: data,
});
column1, _ := column.NewNullableColumnFloat("price",
[]float32{99.99, 59.99},
[]bool{true, false, false, false, true, false})
column2, _ := column.NewNullableColumnInt64("age",
[]int64{25, 30, 45, 60},
[]bool{true, true, false, true, false, true})
_, err = client.Insert(ctx, milvusclient.NewColumnBasedInsertOption("my_collection").
WithInt64Column("pk", []int64{1, 2, 3, 4, 5, 6}).
WithFloatVectorColumn("embedding", 3, [][]float32{
{0.1, 0.2, 0.3},
{0.4, 0.5, 0.6},
{0.2, 0.3, 0.1},
{0.9, 0.1, 0.4},
{0.8, 0.5, 0.3},
{0.1, 0.6, 0.9},
}).
WithColumns(column1, column2),
)
if err != nil {
fmt.Println(err.Error())
// handle err
}
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/insert" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"data": [
{"age": 25, "price": 99.99, "pk": 1, "embedding": [0.1, 0.2, 0.3]},
{"age": 30, "price": 149.50, "pk": 2, "embedding": [0.4, 0.5, 0.6]},
{"age": 35, "price": 199.99, "pk": 3, "embedding": [0.7, 0.8, 0.9]}
],
"collectionName": "my_collection"
}'
使用过滤表达式查询
在插入数据后,您可以使用 query
方法获取符合指定条件的所有 Entity。
如下示例演示了获取 age
字段大于 30 的所有 Entity。
- Python
- Java
- NodeJS
- Go
- cURL
filter = 'age > 30'
res = client.query(
collection_name="my_collection",
filter=filter,
output_fields=["age", "price", "pk"]
)
print(res)
# Example output:
# data: [
# "{'age': 45, 'price': None, 'pk': 4}",
# "{'age': 60, 'price': None, 'pk': 6}"
# ]
import io.milvus.v2.service.vector.request.QueryReq;
import io.milvus.v2.service.vector.response.QueryResp;
String filter = "age > 30";
QueryResp resp = client.query(QueryReq.builder()
.collectionName("my_collection")
.filter(filter)
.outputFields(Arrays.asList("age", "price", "pk"))
.build());
System.out.println(resp.getQueryResults());
// Output
//
// [
// QueryResp.QueryResult(entity={price=null, pk=4, age=45}),
// QueryResp.QueryResult(entity={price=null, pk=6, age=60})
// ]
client.query({
collection_name: 'my_collection',
filter: 'age > 30',
output_fields: ['age', 'price', 'pk']
});
filter := "age > 30"
queryResult, err := client.Query(ctx, milvusclient.NewQueryOption("my_collection").
WithFilter(filter).
WithOutputFields("pk", "age", "price"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
fmt.Println("pk", queryResult.GetColumn("pk").FieldData().GetScalars())
fmt.Println("age", queryResult.GetColumn("age").FieldData().GetScalars())
fmt.Println("price", queryResult.GetColumn("price").FieldData().GetScalars())
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/query" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"filter": "age > 30",
"outputFields": ["age","price", "pk"]
}'
## {"code":0,"cost":0,"data":[{"age":30,"pk":2,"price":149.5},{"age":35,"pk":3,"price":199.99}]}
如下示例演示了获取 price
字段为 null 的所有 Entity。
- Python
- Java
- NodeJS
- Go
- cURL
filter = 'price is null'
res = client.query(
collection_name="my_collection",
filter=filter,
output_fields=["age", "price", "pk"]
)
print(res)
# Example output:
# data: [
# "{'age': 30, 'price': None, 'pk': 2}",
# "{'age': 18, 'price': None, 'pk': 3}",
# "{'age': 45, 'price': None, 'pk': 4}",
# "{'age': 60, 'price': None, 'pk': 6}"
# ]
String filter = "price is null";
QueryResp resp = client.query(QueryReq.builder()
.collectionName("my_collection")
.filter(filter)
.outputFields(Arrays.asList("age", "price", "pk"))
.build());
System.out.println(resp.getQueryResults());
// Output
// [
// QueryResp.QueryResult(entity={price=null, pk=2, age=30}),
// QueryResp.QueryResult(entity={price=null, pk=3, age=18}),
// QueryResp.QueryResult(entity={price=null, pk=4, age=45}),
// QueryResp.QueryResult(entity={price=null, pk=6, age=60})
// ]
// node
const filter = 'price is null';
const res = await client.query({
collection_name:"my_collection",
filter:filter,
output_fields=["age", "price", "pk"]
});
console.log(res);
// Example output:
// data: [
// "{'age': 18, 'price': None, 'pk': 3}",
// "{'age': 18, 'price': 59.99, 'pk': 5}"
// ]
filter = "price is null"
queryResult, err = client.Query(ctx, milvusclient.NewQueryOption("my_collection").
WithFilter(filter).
WithOutputFields("pk", "age", "price"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
fmt.Println("pk", queryResult.GetColumn("pk"))
fmt.Println("age", queryResult.GetColumn("age"))
fmt.Println("price", queryResult.GetColumn("price"))
# restful
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/query" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"filter": "price is null",
"outputFields": ["age", "price", "pk"]
}'
如需获取 age
字段为 18
的所有 Entity,可以参考如下示例。由于 18
为 age
字段的默认值,查询结果将包含该字段显式设置为 18
以及设置为 null 的所有 Entity。
- Python
- Java
- NodeJS
- Go
- cURL
filter = 'age == 18'
res = client.query(
collection_name="my_collection",
filter=filter,
output_fields=["age", "price", "pk"]
)
print(res)
# Example output:
# data: [
# "{'age': 18, 'price': None, 'pk': 3}",
# "{'age': 18, 'price': 59.99, 'pk': 5}"
# ]
String filter = "age == 18";
QueryResp resp = client.query(QueryReq.builder()
.collectionName("my_collection")
.filter(filter)
.outputFields(Arrays.asList("age", "price", "pk"))
.build());
System.out.println(resp.getQueryResults());
// Output
// [
// QueryResp.QueryResult(entity={price=null, pk=3, age=18}),
// QueryResp.QueryResult(entity={price=59.99, pk=5, age=18})
// ]
// node
const filter = 'age == 18';
const res = await client.query({
collection_name:"my_collection",
filter:filter,
output_fields=["age", "price", "pk"]
});
console.log(res);
// Example output:
// data: [
// "{'age': 18, 'price': None, 'pk': 3}",
// "{'age': 18, 'price': 59.99, 'pk': 5}"
// ]
filter = "age == 18"
queryResult, err = client.Query(ctx, milvusclient.NewQueryOption("my_collection").
WithFilter(filter).
WithOutputFields("pk", "age", "price"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
fmt.Println("pk", queryResult.GetColumn("pk"))
fmt.Println("age", queryResult.GetColumn("age"))
fmt.Println("price", queryResult.GetColumn("price"))
# restful
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/query" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"filter": "age == 18",
"outputFields": ["age", "price", "pk"]
}'
使用过滤表达式的向量查询
除了简单的基于数值的过滤查询外,您还可以将向量相似性搜索和过滤表达式结合。如下示例演示了如何在向量搜索中添加过滤表达式。
- Python
- Java
- NodeJS
- Go
- cURL
filter = "25 <= age <= 35"
res = client.search(
collection_name="my_collection",
data=[[0.3, -0.6, 0.1]],
limit=5,
search_params={"params": {"nprobe": 10}},
output_fields=["age","price"],
filter=filter
)
print(res)
# Example output:
# data: [
# "[{'id': 2, 'distance': -0.2016308456659317, 'entity': {'age': 30, 'price': None}}, {'id': 1, 'distance': -0.23643313348293304, 'entity': {'age': 25, 'price': 99.98999786376953}}]"
# ]
import io.milvus.v2.service.vector.request.SearchReq;
import io.milvus.v2.service.vector.request.data.FloatVec;
import io.milvus.v2.service.vector.response.SearchResp;
String filter = "25 <= age <= 35";
SearchResp resp = client.search(SearchReq.builder()
.collectionName("my_collection")
.annsField("embedding")
.data(Collections.singletonList(new FloatVec(new float[]{0.3f, -0.6f, 0.1f})))
.topK(5)
.outputFields(Arrays.asList("age", "price"))
.filter(filter)
.build());
System.out.println(resp.getSearchResults());
// Output
//
// [
// [
// SearchResp.SearchResult(entity={price=null, age=30}, score=-0.20163085, id=2),
// SearchResp.SearchResult(entity={price=99.99, age=25}, score=-0.23643313, id=1)
// ]
// ]
await client.search({
collection_name: 'my_collection',
data: [0.3, -0.6, 0.1],
limit: 5,
output_fields: ['age', 'price'],
filter: '25 <= age <= 35'
});
queryVector := []float32{0.3, -0.6, 0.1}
filter = "25 <= age <= 35"
annParam := index.NewCustomAnnParam()
annParam.WithExtraParam("nprobe", 10)
resultSets, err := client.Search(ctx, milvusclient.NewSearchOption(
"my_collection", // collectionName
5, // limit
[]entity.Vector{entity.FloatVector(queryVector)},
).WithANNSField("embedding").
WithFilter(filter).
WithAnnParam(annParam).
WithOutputFields("age", "price"))
if err != nil {
fmt.Println(err.Error())
// handle error
}
for _, resultSet := range resultSets {
fmt.Println("IDs: ", resultSet.IDs.FieldData().GetScalars())
fmt.Println("Scores: ", resultSet.Scores)
fmt.Println("age: ", resultSet.GetColumn("age"))
fmt.Println("price: ", resultSet.GetColumn("price"))
}
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/search" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
-d '{
"collectionName": "my_collection",
"data": [
[0.3, -0.6, 0.1]
],
"annsField": "embedding",
"limit": 5,
"outputFields": ["age", "price"]
}'
## {"code":0,"cost":0,"data":[{"age":35,"distance":-0.19054288,"id":3,"price":199.99},{"age":30,"distance":-0.20163085,"id":2,"price":149.5},{"age":25,"distance":-0.2364331,"id":1,"price":99.99}]}
在该示例中,我们首先定义了一个查询向量,然后添加了一个过滤表达式 25 <= age <= 35
。查询结果除了与查询向量在语义上相关外,还需要满足过滤表达式的要求。关于过滤查询的更多内容,可以参考 Filtered Search。