Lowercase

Lowercase 过滤器将分词器生成的词项转换为小写，使搜索不区分大小写。例如，它可以将 ["High", "Performance", "Vector", "Database"] 转换为 ["high", "performance", "vector", "database"]。

配置

Lowercase 过滤器内置于 Zilliz Cloud。要使用它，只需在 analyzer_params 的过滤器部分指定其名称。

Python

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

Java

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

NodeJS

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

Go

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

cURL

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

Lowercase 过滤器作用于分词器生成的词项，因此必须与分词器结合使用。有关 Zilliz Cloud 中可用的分词器列表，请参阅分词器参考。

定义 analyzer_params 后，您可以在定义 Collection Schema 时将其应用于 VARCHAR 字段。这使得 Zilliz Cloud 能够使用指定的分析器处理该字段中的文本，以实现高效的分词和过滤。更多信息，请参阅使用示例。

使用示例

在完成 Analyzer 配置后，您可以使用 run_analyzer 方法来验证分词效果是否符合预期。

Analyzer 配置

Python

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

Java

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

NodeJS

// javascript

Go

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

cURL

# restful

使用 run_analyzer 验证效果

Python

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(
    uri="YOUR_CLUSTER_ENDPOINT",
    token="YOUR_CLUSTER_TOKEN"
)

# Sample text to analyze
sample_text = "The Lowercase Filter Ensures Uniformity In Text Processing."

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

Java

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("YOUR_CLUSTER_ENDPOINT")
        .token("YOUR_CLUSTER_TOKEN")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

List<String> texts = new ArrayList<>();
texts.add("The Lowercase Filter Ensures Uniformity In Text Processing.");

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

NodeJS

// javascript

Go

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

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

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

bs, _ := json.Marshal(analyzerParams)
texts := []string{"The Lowercase Filter Ensures Uniformity In Text Processing."}
option := milvusclient.NewRunAnalyzerOption(texts).
    WithAnalyzerParams(string(bs))

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

cURL

# restful

预期结果

['the', 'lowercase', 'filter', 'ensures', 'uniformity', 'in', 'text', 'processing']