詞幹

stemmer 過濾器可將字詞還原為其基本或字根形式（稱為詞幹化），使其更容易匹配不同轉折中具有類似涵義的字詞。stemmer 過濾器支援多種語言，可在各種語言環境中進行有效的搜尋與索引。

設定

stemmer 篩選器是 Milvus 的自訂篩選器。若要使用它，請在篩選器設定中指定"type": "stemmer" ，以及language 參數，以選擇所需的語言進行詞幹處理。

analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "stemmer", # Specifies the filter type as stemmer
        "language": "english", # Sets the language for stemming to English
    }],
}

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "standard");
analyzerParams.put("filter",
        Collections.singletonList(
                new HashMap<String, Object>() {{
                    put("type", "stemmer");
                    put("language", "english");
                }}
        )
);

const analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "stemmer", // Specifies the filter type as stop
        "language": "english", 
    }],
};

analyzerParams = map[string]any{"tokenizer": "standard",
    "filter": []any{map[string]any{
        "type":     "stemmer",
        "language": "english",
    }}}

# restful
analyzerParams='{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "stemmer",
      "language": "english"
    }
  ]
}'

stemmer 過濾器接受下列可設定的參數。

參數	說明
language	指定詞幹處理的語言。支援的語言包括"arabic","danish","dutch","english","finnish","french","german","greek","hungarian","italian","norwegian","portuguese","romanian","russian","spanish","swedish","tamil" 、"turkish"

stemmer 過濾器會對 tokenizer 產生的詞彙進行操作，因此必須與 tokenizer 結合使用。

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": "standard",
    "filter":[{
        "type": "stemmer", # Specifies the filter type as stemmer
        "language": "english", # Sets the language for stemming to English
    }],
}

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "standard");
analyzerParams.put("filter",
        Collections.singletonList(
                new HashMap<String, Object>() {{
                    put("type", "stemmer");
                    put("language", "english");
                }}
        )
);

// javascript

analyzerParams = map[string]any{"tokenizer": "standard",
    "filter": []any{map[string]any{
        "type":     "stemmer",
        "language": "english",
    }}}

# restful
analyzerParams='{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "stemmer",
      "language": "english"
    }
  ]
}'

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 = "running runs looked ran runner"

# 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("running runs looked ran runner");

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{"running runs looked ran runner"}
option := milvusclient.NewRunAnalyzerOption(texts).
    WithAnalyzerParams(string(bs))

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

# restful
not support yet

預期輸出

['run', 'run', 'look', 'ran', 'runner']