Number 字段

Number 字段是存储数值的标量字段。这些值可以是整数（整型）或小数（浮点数）。它们通常用于表示数量、测量值或任何需要进行数学处理的数据。

下表描述了 Milvus 中可用的数字字段数据类型。

字段类型	描述
BOOL	布尔类型，用于存储 true 或 false，适合描述二进制状态。
INT8	8 位整数，适合存储小范围的整数数据。
INT16	16 位整数，用于中等范围的整数数据。
INT32	32 位整数，适合一般整数数据存储，如产品数量或用户 ID。
INT64	64 位整数，适合存储大范围数据，如时间戳或标识符。
FLOAT	32 位浮点数，用于需要一般精度的数据，如评分或温度。
DOUBLE	64 位双精度浮点数，用于高精度数据，如财务信息或科学计算。

要声明数字字段，只需将 datatype 设置为可用的数值数据类型之一。例如，DataType.INT64 用于整数字段，DataType.FLOAT 用于浮点字段。

Milvus 支持数字字段的空值和默认值。要启用这些功能，请将 nullable 设置为 True，并将 default_value 设置为数值。有关详细信息，请参阅 可空值与默认值。

添加数字字段

要存储数值数据，请在 collection schema 中定义数字字段。以下是包含两个数字字段的 collection schema 示例：

• age：存储整数数据，允许空值，默认值为 18。

• price：存储浮点数据，允许空值，但没有默认值。

如果在定义 schema 时设置 enable_dynamic_fields=True，Milvus 允许您插入事先未定义的标量字段。但是，这可能会增加查询和管理的复杂性，可能影响性能。有关更多信息，请参阅 Dynamic Field。

PythonJavaNodeJSGocURL

# Import necessary libraries
from pymilvus import MilvusClient, DataType

# Define server address
SERVER_ADDR = "http://localhost:19530"

# 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)
# 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("http://localhost:19530")
        .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("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: "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),
)

export int64Field='{
    "fieldName": "age",
    "dataType": "Int64"
}'

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,
        $floatField,
        $pkField,
        $vectorField
    ]
}"

Set index params

Indexing helps improve search and query performance. In Milvus, indexing is mandatory for vector fields but optional for scalar fields.

The following example creates indexes on the vector field embedding and the scalar field age, both using the AUTOINDEX index type. With this type, Milvus automatically selects the most suitable index based on the data type. You can also customize the index type and params for each field. For details, refer to Index Explained.

PythonJavaNodeJSGocURL

# 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"
        }
    ]'

Create collection

Once the schema and indexes are defined, create a collection that includes number fields.

PythonJavaNodeJSGocURL

# 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
}"

Insert data

After creating the collection, insert entities that match the schema.

PythonJavaNodeJSGocURL

# 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"
}'

Query with filter expressions

After inserting entities, use the query method to retrieve entities that match the specified filter expressions.

To retrieve entities where the age is greater than 30:

PythonJavaNodeJSGocURL

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}]}

To retrieve entities where the price is null:

PythonJavaNodeJSGocURL

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"]
}'

To retrieve entities where age has the value 18, use the following expression below. As the default value of age is 18, the expected result should include entities with age explicitly set to 18 or with age set to null.

PythonJavaNodeJSGocURL

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"]
}'

Vector search with filter expressions

In addition to basic number field filtering, you can combine vector similarity searches with number field filters. For example, the following code shows how to add a number field filter to a vector search:

PythonJavaNodeJSGocURL

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}]}

In this example, we first define a query vector and add a filter condition 25 <= age <= 35 during the search. This ensures that the search results are not only similar to the query vector but also meet the specified age range. For more information, refer to Filtering.