Decompounder

decompounder 过滤器根据指定的字典将复合词拆分为单个组成部分，从而更容易搜索复合术语的部分。该过滤器对于经常使用复合词的语言（如德语）特别有用。

配置

decompounder 过滤器是 Zilliz Cloud 中的自定义过滤器，通过在过滤器配置中设置 "type": "decompounder" 并将word_list设置为您需要的值的方式来指定。

Python

analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "decompounder", # Specifies the filter type as decompounder
        "word_list": ["dampf", "schiff", "fahrt", "brot", "backen", "automat"],
    }],
}

Java

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "standard");
analyzerParams.put("filter",
        Collections.singletonList(
                new HashMap<String, Object>() {{
                    put("type", "decompounder");
                    put("word_list", Arrays.asList("dampf", "schiff", "fahrt", "brot", "backen", "automat"));
                }}
        )
);

NodeJS

const analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "decompounder", // Specifies the filter type as decompounder
        "word_list": ["dampf", "schiff", "fahrt", "brot", "backen", "automat"],
    }],
};

Go

analyzerParams = map[string]any{"tokenizer": "standard",
    "filter": []any{map[string]any{
        "type":       "decompounder",
        "word_list": []string{"dampf", "schiff", "fahrt", "brot", "backen", "automat"},
    }}}

cURL

# restful
analyzerParams='{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "decompounder",
      "word_list": [
        "dampf",
        "schiff",
        "fahrt",
        "brot",
        "backen",
        "automat"
      ]
    }
  ]
}'

decompounder 过滤器接受以下可选参数。

参数	描述
word_list	用于拆分复合术语的词组件列表。该字典决定了复合词如何被分解为单个术语。

decompounder 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。

示例输出

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":[{
        "type": "decompounder", # Specifies the filter type as decompounder
        "word_list": ["dampf", "schiff", "fahrt", "brot", "backen", "automat"],
    }],
}

Java

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", "standard");
analyzerParams.put("filter",
        Collections.singletonList(
                new HashMap<String, Object>() {{
                    put("type", "decompounder");
                    put("word_list", Arrays.asList("dampf", "schiff", "fahrt", "brot", "backen", "automat"));
                }}
        )
);

NodeJS

// javascript

Go

analyzerParams = map[string]any{"tokenizer": "standard",
    "filter": []any{map[string]any{
        "type":       "decompounder",
        "word_list": []string{"dampf", "schiff", "fahrt", "brot", "backen", "automat"},
    }}}

cURL

# restful
analyzerParams='{
  "tokenizer": "standard",
  "filter": [
    {
      "type": "decompounder",
      "word_list": [
        "dampf",
        "schiff",
        "fahrt",
        "brot",
        "backen",
        "automat"
      ]
    }
  ]
}'

使用 run_analyzer 验证效果

Python

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(uri="YOUR_CLUSTER_ENDPOINT")

# Sample text to analyze
sample_text = "dampfschifffahrt brotbackautomat"

# 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")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

List<String> texts = new ArrayList<>();
texts.add("dampfschifffahrt brotbackautomat");

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{"dampfschifffahrt brotbackautomat"}
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

['dampf', 'schiff', 'fahrt', 'brotbackautomat']