VarChar-Feld

Milvus unterstützt skalare Textdaten mit den Feldern „ VARCHAR “ und „ TEXT “. Auf dieser Seite wird das Feld „ VARCHAR “ beschrieben, das für kurze, begrenzte Zeichenfolgen-Metadaten wie Namen, Tags, Kategorien und externe IDs vorgesehen ist.

Für längere Quelltexte, Dokumentpassagen, Artikeltexte, Tickets oder Protokolle, die zusammen mit Entitäten gespeichert und zurückgegeben werden sollen, verwenden Sie stattdessen ein „ TEXT “-Feld. Verwenden Sie „ TEXT “, wenn ein Wert die „ 65,535 “-Byte-Grenze überschreiten könnte oder wenn Sie keine feste „ max_length “ im Sammlungsschema festlegen möchten. Weitere Informationen finden Sie unter „Textfeld“.

Wenn Sie ein Feld vom Typ „ VARCHAR “ definieren, sind zwei Parameter obligatorisch:

• Legen Sie die „ datatype “ auf „ DataType.VARCHAR “ fest.

• Geben Sie die „ max_length “ an, die die maximale Anzahl an Bytes definiert, die das Feld „ VARCHAR “ speichern kann. Der gültige Bereich für „ max_length “ liegt zwischen 1 und 65.535.

VARCHAR-Feld hinzufügen

Um kurze, begrenzte Zeichenfolgen-Metadaten in Milvus zu speichern, definieren Sie ein Feld vom Typ „ VARCHAR “ in Ihrem Sammlungsschema. Nachfolgend finden Sie ein Beispiel für die Definition eines Sammlungsschemas mit zwei Feldern vom Typ „ VARCHAR “:

• varchar_field1: speichert bis zu 100 Byte, erlaubt Nullwerte und hat den Standardwert „ "Unknown" “.

• varchar_field2: speichert bis zu 200 Byte, erlaubt Nullwerte, hat jedoch keinen Standardwert.

# 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 `varchar_field1` that supports null values with default value "Unknown"
schema.add_field(field_name="varchar_field1", datatype=DataType.VARCHAR, max_length=100, nullable=True, default_value="Unknown")
# Add `varchar_field2` that supports null values without default value
schema.add_field(field_name="varchar_field2", datatype=DataType.VARCHAR, max_length=200, 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("varchar_field1")
        .dataType(DataType.VarChar)
        .maxLength(100)
        .isNullable(true)
        .defaultValue("Unknown")
        .build());

schema.addField(AddFieldReq.builder()
        .fieldName("varchar_field2")
        .dataType(DataType.VarChar)
        .maxLength(200)
        .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 client = new MilvusClient({
  address: `http://localhost:19530`
});

const schema = [
  {
    name: "metadata",
    data_type: DataType.JSON,
  },
  {
    name: "pk",
    data_type: DataType.Int64,
    is_primary_key: true,
  },
  {
    name: "varchar_field2",
    data_type: DataType.VarChar,
    max_length: 200,
  },
  {
    name: "varchar_field1",
    data_type: DataType.VarChar,
    max_length: 100,
  },
];

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("varchar_field1").
    WithDataType(entity.FieldTypeVarChar).
    WithMaxLength(100).
    WithNullable(true).
    WithDefaultValueString("Unknown"),
).WithField(entity.NewField().
    WithName("varchar_field2").
    WithDataType(entity.FieldTypeVarChar).
    WithMaxLength(200).
    WithNullable(true),
)

export varcharField1='{
    "fieldName": "varchar_field1",
    "dataType": "VarChar",
    "elementTypeParams": {
        "max_length": 100
    },
    "nullable": true
}'

export varcharField2='{
    "fieldName": "varchar_field2",
    "dataType": "VarChar",
    "elementTypeParams": {
        "max_length": 200
    },
    "nullable": true
}'

export primaryField='{
    "fieldName": "pk",
    "dataType": "Int64",
    "isPrimary": true
}'

export vectorField='{
    "fieldName": "embedding",
    "dataType": "FloatVector",
    "elementTypeParams": {
        "dim": 3
    }
}'

export schema="{
    \"autoID\": false,
    \"fields\": [
        $varcharField1,
        $varcharField2,
        $primaryField,
        $vectorField
    ]
}"

Indexparameter festlegen

Die Indizierung trägt zur Verbesserung der Such- und Abfrageleistung bei. In Milvus ist die Indizierung für Vektorfelder obligatorisch, für Skalarfelder jedoch optional.

Das folgende Beispiel erstellt Indizes für das Vektorfeld „ embedding “ und das Skalarfeld „ varchar_field1 “, beide unter Verwendung des Indextyps „ AUTOINDEX “. Bei diesem Typ wählt Milvus automatisch den am besten geeigneten Index basierend auf dem Datentyp aus. Sie können den Indextyp und die Parameter auch für jedes Feld individuell anpassen. Weitere Informationen finden Sie unter „Index Explained“.

# Set index params

index_params = client.prepare_index_params()

# Index `varchar_field1` with AUTOINDEX
index_params.add_index(
    field_name="varchar_field1",
    index_type="AUTOINDEX",
    index_name="varchar_index"
)

# Index `embedding` with AUTOINDEX and specify 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("varchar_field1")
        .indexName("varchar_index")
        .indexType(IndexParam.IndexType.AUTOINDEX)
        .build());
        
indexes.add(IndexParam.builder()
        .fieldName("embedding")
        .indexType(IndexParam.IndexType.AUTOINDEX)
        .metricType(IndexParam.MetricType.COSINE)
        .build());

indexOption1 := milvusclient.NewCreateIndexOption("my_collection", "embedding",
    index.NewAutoIndex(index.MetricType(entity.IP)))
indexOption2 := milvusclient.NewCreateIndexOption("my_collection", "varchar_field1",
    index.NewInvertedIndex())

const indexParams = [{
    index_name: 'varchar_index',
    field_name: 'varchar_field1',
    index_type: IndexType.AUTOINDEX,
)];

indexParams.push({
    index_name: 'embedding_index',
    field_name: 'embedding',
    metric_type: MetricType.COSINE,
    index_type: IndexType.AUTOINDEX,
});

export indexParams='[
        {
            "fieldName": "varchar_field1",
            "indexName": "varchar_index",
            "indexType": "AUTOINDEX"
        }
    ]'
    
export indexParams='[
        {
            "fieldName": "varchar_field1",
            "indexName": "varchar_index",
            "indexType": "AUTOINDEX"
        },
        {
            "fieldName": "embedding",
            "metricType": "COSINE",
            "indexType": "AUTOINDEX"
        }
    ]'

Sammlung erstellen

Sobald das Schema und der Index definiert sind, erstellen Sie eine Sammlung, die Zeichenfolgenfelder enthält.

# 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);

err = client.CreateCollection(ctx,
    milvusclient.NewCreateCollectionOption("my_collection", schema).
        WithIndexOptions(indexOption1, indexOption2))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

await client.create_collection({
    collection_name: "my_collection",
    schema: schema,
    index_params: index_params
});

curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/collections/create" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--header "Request-Timeout: 10" \
-d "{
    \"collectionName\": \"my_collection\",
    \"schema\": $schema,
    \"indexParams\": $indexParams
}"
## {"code":0,"data":{}}

Daten einfügen

Fügen Sie nach dem Erstellen der Sammlung Entitäten ein, die dem Schema entsprechen.

# Sample data
data = [
    {"varchar_field1": "Product A", "varchar_field2": "High quality product", "pk": 1, "embedding": [0.1, 0.2, 0.3]},
    {"varchar_field1": "Product B", "pk": 2, "embedding": [0.4, 0.5, 0.6]}, # varchar_field2 field is missing, which should be NULL
    {"varchar_field1": None, "varchar_field2": None, "pk": 3, "embedding": [0.2, 0.3, 0.1]},  # `varchar_field1` should default to `Unknown`, `varchar_field2` is NULL
    {"varchar_field1": "Product C", "varchar_field2": None, "pk": 4, "embedding": [0.5, 0.7, 0.2]},  # `varchar_field2` is NULL
    {"varchar_field1": None, "varchar_field2": "Exclusive deal", "pk": 5, "embedding": [0.6, 0.4, 0.8]},  # `varchar_field1` should default to `Unknown`
    {"varchar_field1": "Unknown", "varchar_field2": None, "pk": 6, "embedding": [0.8, 0.5, 0.3]},  # `varchar_field2` is NULL
    {"varchar_field1": "", "varchar_field2": "Best seller", "pk": 7, "embedding": [0.8, 0.5, 0.3]}, # Empty string is not treated as NULL
]

# Insert data
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("{\"varchar_field1\": \"Product A\", \"varchar_field2\": \"High quality product\", \"pk\": 1, \"embedding\": [0.1, 0.2, 0.3]}", JsonObject.class));
rows.add(gson.fromJson("{\"varchar_field1\": \"Product B\", \"pk\": 2, \"embedding\": [0.4, 0.5, 0.6]}", JsonObject.class));
rows.add(gson.fromJson("{\"varchar_field1\": null, \"varchar_field2\": null, \"pk\": 3, \"embedding\": [0.2, 0.3, 0.1]}", JsonObject.class));
rows.add(gson.fromJson("{\"varchar_field1\": \"Product C\", \"varchar_field2\": null, \"pk\": 4, \"embedding\": [0.5, 0.7, 0.2]}", JsonObject.class));
rows.add(gson.fromJson("{\"varchar_field1\": null, \"varchar_field2\": \"Exclusive deal\", \"pk\": 5, \"embedding\": [0.6, 0.4, 0.8]}", JsonObject.class));
rows.add(gson.fromJson("{\"varchar_field1\": \"Unknown\", \"varchar_field2\": null, \"pk\": 6, \"embedding\": [0.8, 0.5, 0.3]}", JsonObject.class));
rows.add(gson.fromJson("{\"varchar_field1\": \"\", \"varchar_field2\": \"Best seller\", \"pk\": 7, \"embedding\": [0.8, 0.5, 0.3]}", JsonObject.class));

InsertResp insertR = client.insert(InsertReq.builder()
        .collectionName("my_collection")
        .data(rows)
        .build());

column1, _ := column.NewNullableColumnVarChar("varchar_field1",
    []string{"Product A", "Product B", "Product C", "Unknown", ""},
    []bool{true, true, false, true, false, true, true})
column2, _ := column.NewNullableColumnVarChar("varchar_field2",
    []string{"High quality product", "Exclusive deal", "Best seller"},
    []bool{true, false, false, false, true, false, true})

_, err = client.Insert(ctx, milvusclient.NewColumnBasedInsertOption("my_collection").
    WithInt64Column("pk", []int64{1, 2, 3, 4, 5, 6, 7}).
    WithFloatVectorColumn("embedding", 3, [][]float32{
        {0.1, 0.2, 0.3},
        {0.4, 0.5, 0.6},
        {0.2, 0.3, 0.1},
        {0.5, 0.7, 0.2},
        {0.6, 0.4, 0.8},
        {0.8, 0.5, 0.3},
        {0.8, 0.5, 0.3},
    }).
    WithColumns(column1, column2),
)
if err != nil {
    fmt.Println(err.Error())
    // handle err
}

const data = [
  {
    varchar_field1: "Product A",
    varchar_field2: "High quality product",
    pk: 1,
    embedding: [0.1, 0.2, 0.3],
  },
  {
    varchar_field1: "Product B",
    varchar_field2: "Affordable price",
    pk: 2,
    embedding: [0.4, 0.5, 0.6],
  },
  {
    varchar_field1: "Product C",
    varchar_field2: "Best seller",
    pk: 3,
    embedding: [0.7, 0.8, 0.9],
  },
];

await client.insert({
  collection_name: "my_collection",
  data: data,
});

curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/insert" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--header "Request-Timeout: 10" \
--data '{
    "data": [
        {"varchar_field1": "Product A", "varchar_field2": "High quality product", "pk": 1, "embedding": [0.1, 0.2, 0.3]},
        {"varchar_field1": "Product B", "pk": 2, "embedding": [0.4, 0.5, 0.6]},
        {"varchar_field1": null, "varchar_field2": null, "pk": 3, "embedding": [0.2, 0.3, 0.1]},  
        {"varchar_field1": "Product C", "varchar_field2": null, "pk": 4, "embedding": [0.5, 0.7, 0.2]},  
        {"varchar_field1": null, "varchar_field2": "Exclusive deal", "pk": 5, "embedding": [0.6, 0.4, 0.8]},  
        {"varchar_field1": "Unknown", "varchar_field2": null, "pk": 6, "embedding": [0.8, 0.5, 0.3]},  
        {"varchar_field1": "", "varchar_field2": "Best seller", "pk": 7, "embedding": [0.8, 0.5, 0.3]}  
    ],
    "collectionName": "my_collection"
}'

## {"code":0,"cost":0,"data":{"insertCount":3,"insertIds":[1,2,3]}}

Abfrage mit Filterausdrücken

Verwenden Sie nach dem Einfügen der Entitäten die Methode „ query “, um Entitäten abzurufen, die den angegebenen Filterausdrücken entsprechen.

Um Entitäten abzurufen, bei denen der Wert von ` varchar_field1 ` mit der Zeichenfolge ` "Product A"` übereinstimmt:

# Filter `varchar_field1` with value "Product A"
filter = 'varchar_field1 == "Product A"'

res = client.query(
    collection_name="my_collection",
    filter=filter,
    output_fields=["varchar_field1", "varchar_field2"]
)

print(res)

# Example output:
# data: [
#     "{'varchar_field1': 'Product A', 'varchar_field2': 'High quality product', 'pk': 1}"
# ]

import io.milvus.v2.service.vector.request.QueryReq;
import io.milvus.v2.service.vector.response.QueryResp;

String filter = "varchar_field1 == \"Product A\"";
QueryResp resp = client.query(QueryReq.builder()
        .collectionName("my_collection")
        .filter(filter)
        .outputFields(Arrays.asList("varchar_field1", "varchar_field2"))
        .build());

System.out.println(resp.getQueryResults());

// Output
//
// [QueryResp.QueryResult(entity={varchar_field1=Product A, varchar_field2=High quality product, pk=1})]

filter := "varchar_field1 == \"Product A\""
queryResult, err := client.Query(ctx, milvusclient.NewQueryOption("my_collection").
    WithFilter(filter).
    WithOutputFields("varchar_field1", "varchar_field2"))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}
fmt.Println("varchar_field1", queryResult.GetColumn("varchar_field1").FieldData().GetScalars())
fmt.Println("varchar_field2", queryResult.GetColumn("varchar_field2").FieldData().GetScalars())

// Output
//
// varchar_field1 string_data:{data:"Product A"}
// varchar_field2 string_data:{data:"High quality product"}

await client.query({
    collection_name: 'my_collection',
    filter: 'varchar_field1 == "Product A"',
    output_fields: ['varchar_field1', 'varchar_field2']
});

curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/query" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--header "Request-Timeout: 10" \
-d '{
    "collectionName": "my_collection",
    "filter": "varchar_field1 == \"Product A\"",
    "outputFields": ["varchar_field1", "varchar_field2"]
}'
## {"code":0,"cost":0,"data":[{"pk":1,"varchar_field1":"Product A","varchar_field2":"High quality product"}]}

So rufen Sie Entitäten ab, bei denen der Wert von ` varchar_field2 ` null ist:

# Filter entities where `varchar_field2` is null
filter = 'varchar_field2 is null'

res = client.query(
    collection_name="my_collection",
    filter=filter,
    output_fields=["varchar_field1", "varchar_field2"]
)

print(res)

# Example output:
# data: [
#     "{'varchar_field1': 'Product B', 'varchar_field2': None, 'pk': 2}",
#     "{'varchar_field1': 'Unknown', 'varchar_field2': None, 'pk': 3}",
#     "{'varchar_field1': 'Product C', 'varchar_field2': None, 'pk': 4}",
#     "{'varchar_field1': 'Unknown', 'varchar_field2': None, 'pk': 6}"
# ]

String filter = "varchar_field2 is null";
QueryResp resp = client.query(QueryReq.builder()
        .collectionName("my_collection")
        .filter(filter)
        .outputFields(Arrays.asList("varchar_field1", "varchar_field2"))
        .build());

System.out.println(resp.getQueryResults());

// Output
//
// [
//    QueryResp.QueryResult(entity={varchar_field1=Product B, varchar_field2=null, pk=2}),
//    QueryResp.QueryResult(entity={varchar_field1=Unknown, varchar_field2=null, pk=3}),
//    QueryResp.QueryResult(entity={varchar_field1=Product C, varchar_field2=null, pk=4}),
//    QueryResp.QueryResult(entity={varchar_field1=Unknown, varchar_field2=null, pk=6})
// ]

filter = "varchar_field2 is null"
queryResult, err = client.Query(ctx, milvusclient.NewQueryOption("my_collection").
    WithFilter(filter).
    WithOutputFields("varchar_field1", "varchar_field2"))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}
fmt.Println("varchar_field1", queryResult.GetColumn("varchar_field1"))
fmt.Println("varchar_field2", queryResult.GetColumn("varchar_field2"))

await client.query({
    collection_name: 'my_collection',
    filter: 'varchar_field2 is null',
    output_fields: ['varchar_field1', 'varchar_field2']
});

# restful
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/query" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--header "Request-Timeout: 10" \
-d '{
    "collectionName": "my_collection",
    "filter": "varchar_field2 is null",
    "outputFields": ["varchar_field1", "varchar_field2"]
}'

Um Entitäten abzurufen, bei denen „ varchar_field1 “ den Wert „ "Unknown" “ hat, verwenden Sie den folgenden Ausdruck. Da der Standardwert von „ varchar_field1 “ „ "Unknown" “ ist, sollte das erwartete Ergebnis Entitäten enthalten, bei denen „ varchar_field1 “ explizit auf „ "Unknown" “ gesetzt ist oder bei denen „ varchar_field1 “ auf null gesetzt ist.

# Filter entities with `varchar_field1` with value `Unknown`
filter = 'varchar_field1 == "Unknown"'

res = client.query(
    collection_name="my_collection",
    filter=filter,
    output_fields=["varchar_field1", "varchar_field2"]
)

print(res)

# Example output:
# data: [
#     "{'varchar_field1': 'Unknown', 'varchar_field2': None, 'pk': 3}",
#     "{'varchar_field1': 'Unknown', 'varchar_field2': 'Exclusive deal', 'pk': 5}",
#     "{'varchar_field1': 'Unknown', 'varchar_field2': None, 'pk': 6}"
# ]

String filter = "varchar_field1 == \"Unknown\"";
QueryResp resp = client.query(QueryReq.builder()
        .collectionName("my_collection")
        .filter(filter)
        .outputFields(Arrays.asList("varchar_field1", "varchar_field2"))
        .build());

System.out.println(resp.getQueryResults());

// Output
// 
// [
//    QueryResp.QueryResult(entity={varchar_field1=Unknown, varchar_field2=null, pk=3}),
//    QueryResp.QueryResult(entity={varchar_field1=Unknown, varchar_field2=Exclusive deal, pk=5}),
//    QueryResp.QueryResult(entity={varchar_field1=Unknown, varchar_field2=null, pk=6})
// ]

filter = "varchar_field1 == \"Unknown\""
queryResult, err = client.Query(ctx, milvusclient.NewQueryOption("my_collection").
    WithFilter(filter).
    WithOutputFields("varchar_field1", "varchar_field2"))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}
fmt.Println("varchar_field1", queryResult.GetColumn("varchar_field1"))
fmt.Println("varchar_field2", queryResult.GetColumn("varchar_field2"))

// node
await client.query({
    collection_name: 'my_collection',
    filter: 'varchar_field1 == "Unknown"',
    output_fields: ['varchar_field1', 'varchar_field2']
});

# restful
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/query" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--header "Request-Timeout: 10" \
-d '{
    "collectionName": "my_collection",
    "filter": "varchar_field1 == \"Unknown\"",
    "outputFields": ["varchar_field1", "varchar_field2"]
}'

Vektorsuche mit Filterausdrücken

Zusätzlich zur grundlegenden Filterung nach skalaren Feldern können Sie Vektorähnlichkeitssuchen mit Filtern für skalare Felder kombinieren. Der folgende Code zeigt beispielsweise, wie Sie einen Filter für ein skalares Feld zu einer Vektorsuche hinzufügen:

# Search with string filtering

# Filter `varchar_field2` with value "Best seller"
filter = 'varchar_field2 == "Best seller"'

res = client.search(
    collection_name="my_collection",
    data=[[0.3, -0.6, 0.1]],
    limit=5,
    search_params={"params": {"nprobe": 10}},
    output_fields=["varchar_field1", "varchar_field2"],
    filter=filter
)

print(res)

# Example output:
# data: [
#     "[{'id': 7, 'distance': -0.04468163847923279, 'entity': {'varchar_field1': '', 'varchar_field2': 'Best seller'}}]"
# ]

import io.milvus.v2.service.vector.request.SearchReq;
import io.milvus.v2.service.vector.response.SearchResp;

String filter = "varchar_field2 == \"Best seller\"";
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("varchar_field1", "varchar_field2"))
        .filter(filter)
        .build());

System.out.println(resp.getSearchResults());

// Output
//
// [[SearchResp.SearchResult(entity={varchar_field1=, varchar_field2=Best seller}, score=-0.04468164, id=7)]]

queryVector := []float32{0.3, -0.6, 0.1}
filter = "varchar_field2 == \"Best seller\""

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("varchar_field1", "varchar_field2"))
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("varchar_field1: ", resultSet.GetColumn("varchar_field1"))
    fmt.Println("varchar_field2: ", resultSet.GetColumn("varchar_field2"))
}

await client.search({
    collection_name: 'my_collection',
    data: [0.3, -0.6, 0.1],
    limit: 5,
    output_fields: ['varchar_field1', 'varchar_field2'],
    filter: 'varchar_field2 == "Best seller"'
    params: {
       nprobe:10
    }
});

curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/entities/search" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--header "Request-Timeout: 10" \
-d '{
    "collectionName": "my_collection",
    "data": [
        [0.3, -0.6, 0.1]
    ],
    "limit": 5,
    "searchParams":{
        "params":{"nprobe":10}
    },
    "outputFields": ["varchar_field1", "varchar_field2"],
    "filter": "varchar_field2 == \"Best seller\""
}'

## {"code":0,"cost":0,"data":[{"distance":-0.2364331,"id":1,"varchar_field1":"Product A","varchar_field2":"High quality product"}]}