空格

只要字與字之間有空格，whitespace tokenizer 就會將文字分割成詞彙。

配置

若要設定使用whitespace tokenizer 的分析器，請在analyzer_params 中設定tokenizer 為whitespace 。

analyzer_params = {
    "tokenizer": "whitespace",
}

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "whitespace");

const analyzer_params = {
    "tokenizer": "whitespace"
};

analyzerParams = map[string]any{"tokenizer": "whitespace"}

# restful
analyzerParams='{
  "tokenizer": "whitespace"
}'

空白符記器可與一個或多個過濾器結合使用。例如，以下程式碼定義了一個使用whitespace 記錄器及lowercase 過濾器的分析器：

analyzer_params = {
    "tokenizer": "whitespace",
    "filter": ["lowercase"]
}

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "whitespace");
analyzerParams.put("filter", Collections.singletonList("lowercase"));

const analyzer_params = {
    "tokenizer": "whitespace",
    "filter": ["lowercase"]
};

analyzerParams = map[string]any{"tokenizer": "whitespace", "filter": []any{"lowercase"}}

# restful
analyzerParams='{
  "tokenizer": "whitespace",
  "filter": [
    "lowercase"
  ]
}'

定義analyzer_params 之後，您可以在定義集合模式時，將它們套用到VARCHAR 欄位。這可讓 Milvus 使用指定的分析器來處理該欄位中的文字，以進行有效率的標記化和過濾。詳情請參閱範例使用。

範例

在應用分析器配置到您的收集模式之前，請使用run_analyzer 方法驗證其行為。

分析器配置

analyzer_params = {
    "tokenizer": "whitespace",
    "filter": ["lowercase"]
}

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "whitespace");
analyzerParams.put("filter", Collections.singletonList("lowercase"));

// javascript

analyzerParams = map[string]any{"tokenizer": "whitespace", "filter": []any{"lowercase"}}

# restful

驗證使用run_analyzerCompatible with Milvus 2.5.11+

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(uri="http://localhost:19530")

# Sample text to analyze
sample_text = "The Milvus vector database is built for scale!"

# Run the standard analyzer with the defined configuration
result = client.run_analyzer(sample_text, analyzer_params)
print("Standard analyzer output:", result)

import io.milvus.v2.client.ConnectConfig;
import io.milvus.v2.client.MilvusClientV2;
import io.milvus.v2.service.vector.request.RunAnalyzerReq;
import io.milvus.v2.service.vector.response.RunAnalyzerResp;

ConnectConfig config = ConnectConfig.builder()
        .uri("http://localhost:19530")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

List<String> texts = new ArrayList<>();
texts.add("The Milvus vector database is built for scale!");

RunAnalyzerResp resp = client.runAnalyzer(RunAnalyzerReq.builder()
        .texts(texts)
        .analyzerParams(analyzerParams)
        .build());
List<RunAnalyzerResp.AnalyzerResult> results = resp.getResults();

// javascript

import (
    "context"
    "encoding/json"
    "fmt"

    "github.com/milvus-io/milvus/client/v2/milvusclient"
)

client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
    Address: "localhost:19530",
    APIKey:  "root:Milvus",
})
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

bs, _ := json.Marshal(analyzerParams)
texts := []string{"The Milvus vector database is built for scale!"}
option := milvusclient.NewRunAnalyzerOption(texts).
    WithAnalyzerParams(string(bs))

result, err := client.RunAnalyzer(ctx, option)
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

# restful

預期輸出

['the', 'milvus', 'vector', 'database', 'is', 'built', 'for', 'scale!']