Bidang Angka

Bidang angka adalah bidang skalar yang menyimpan nilai numerik. Nilai-nilai ini dapat berupa bilangan bulat(bilangan bulat) atau bilangan desimal(bilangan titik mengambang). Field ini biasanya digunakan untuk mewakili jumlah, pengukuran, atau data apa pun yang perlu diproses secara matematis.

Tabel di bawah ini menjelaskan tipe data dari field angka yang tersedia di Milvus.

Tipe Bidang	Deskripsi
BOOL	Tipe Boolean untuk menyimpan true atau false, cocok untuk menggambarkan keadaan biner.
INT8	Bilangan bulat 8-bit, cocok untuk menyimpan data bilangan bulat dengan rentang kecil.
INT16	Bilangan bulat 16-bit, untuk data bilangan bulat jarak menengah.
INT32	Bilangan bulat 32-bit, ideal untuk penyimpanan data bilangan bulat umum seperti jumlah produk atau ID pengguna.
INT64	Bilangan bulat 64-bit, cocok untuk menyimpan data jarak jauh seperti stempel waktu atau pengenal.
FLOAT	Angka floating-point 32-bit, untuk data yang membutuhkan presisi umum, seperti peringkat atau suhu.
DOUBLE	Bilangan floating-point presisi ganda 64-bit, untuk data dengan presisi tinggi seperti informasi keuangan atau perhitungan ilmiah.

Untuk mendeklarasikan bidang angka, cukup setel datatype ke salah satu tipe data numerik yang tersedia. Sebagai contoh, DataType.INT64 untuk field bilangan bulat atau DataType.FLOAT untuk field floating-point.

Menambahkan bidang angka

Untuk menyimpan data numerik, tentukan bidang angka dalam skema koleksi Anda. Di bawah ini adalah contoh skema koleksi dengan dua field angka:

• age: menyimpan data integer, mengizinkan nilai null, dan memiliki nilai default 18.

• price: menyimpan data float, mengizinkan nilai null, tetapi tidak memiliki nilai default.

# 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
    ]
}"

Mengatur parameter indeks

Pengindeksan membantu meningkatkan kinerja pencarian dan kueri. Di Milvus, pengindeksan adalah wajib untuk bidang vektor, tetapi opsional untuk bidang skalar.

Contoh berikut ini membuat indeks pada bidang vektor embedding dan bidang skalar age, keduanya menggunakan tipe indeks AUTOINDEX. Dengan tipe ini, Milvus secara otomatis memilih indeks yang paling sesuai berdasarkan tipe data. Anda juga dapat menyesuaikan jenis indeks dan parameter untuk setiap field. Untuk detailnya, lihat Penjelasan Indeks.

# 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"
        }
    ]'

Membuat koleksi

Setelah skema dan indeks didefinisikan, buatlah koleksi yang menyertakan bidang angka.

# 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
}"

Menyisipkan data

Setelah membuat koleksi, masukkan entitas yang sesuai dengan skema.

# 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"
}'

Kueri dengan ekspresi filter

Setelah menyisipkan entitas, gunakan metode query untuk mengambil entitas yang cocok dengan ekspresi filter yang ditentukan.

Untuk mengambil entitas di mana age lebih besar dari 30:

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}]}

Untuk mengambil entitas di mana price bernilai nol:

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"]
}'

Untuk mengambil entitas di mana age memiliki nilai 18, gunakan ekspresi berikut di bawah ini. Karena nilai default dari age adalah 18, hasil yang diharapkan adalah entitas dengan age yang secara eksplisit disetel ke 18 atau dengan age yang disetel ke null.

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"]
}'

Pencarian vektor dengan ekspresi filter

Selain pemfilteran bidang angka dasar, Anda dapat menggabungkan pencarian kemiripan vektor dengan filter bidang angka. Sebagai contoh, kode berikut ini menunjukkan cara menambahkan filter bidang angka ke pencarian vektor:

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}]}

Dalam contoh ini, pertama-tama kita mendefinisikan vektor kueri dan menambahkan kondisi filter 25 <= age <= 35 selama pencarian. Hal ini memastikan bahwa hasil pencarian tidak hanya mirip dengan vektor kueri tetapi juga memenuhi rentang usia yang ditentukan. Untuk informasi lebih lanjut, lihat Memfilter.