分词器

decompounder 过滤器可根据指定词典将复合词拆分成单个成分，从而更方便地搜索复合词的各个部分。该过滤器对于德语等经常使用复合词的语言尤其有用。组件字典可以通过word_list 参数在线提供，也可以通过word_list_file 参数从注册文件资源加载。

配置

decompounder 过滤器可通过word_list 参数以内联方式或通过word_list_file 参数从注册文件资源中接受其组件字典。

内联字表

decompounder 过滤器是 Milvus 的自定义过滤器。要使用该过滤器，请在过滤器配置中指定"type": "decompounder" 以及word_list 参数，后者提供了要识别的单词组件字典。

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

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"));
                }}
        )
);

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

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

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

decompounder 过滤器接受以下可配置参数。

参数	说明
word_list	用于拆分复合词的单词成分列表。该字典决定了如何将复合词分解为单个术语。

decompounder 过滤器对标记化器生成的术语进行操作，因此必须与标记化器结合使用。有关 Milvus 中可用的标记化器列表，请参阅标准标记化器及其同类页面。

定义analyzer_params 后，可以在定义 Collections Schema 时将其应用到VARCHAR 字段。这样，Milvus 就可以使用指定的分析器对该字段中的文本进行处理，从而实现高效的标记化和过滤。详情请参阅示例使用。

从文件资源加载单词组件Compatible with Milvus 3.0.x

对于大型组件字典，尤其是全语言单词表，可将组件存储在文件中，并将该文件注册为远程文件资源，然后通过word_list_file 参数从过滤器中引用该文件。你可以单独使用word_list_file ，也可以与内联word_list 同时使用；当两者都设置时，过滤器会将两个来源合并为一个组件列表。

文件为纯 UTF-8 文本，每行一个组件词。例如

dampf
schiff
fahrt
brot
backen
automat

将文件上传到 Milvus 集群配置使用的对象存储，然后注册：

from pymilvus import MilvusClient

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

# Register the uploaded file under a name you'll reference from analyzer configs.
client.add_file_resource(
    name="de_components",
    path="file/decompounder.txt",    # full S3 object key, including the rootPath prefix
)

通过word_list_file 在过滤器中引用已注册的资源：

analyzer_params = {
    "tokenizer": "standard",
    "filter": [{
        "type": "decompounder",
        "word_list_file": {
            "type": "remote",
            "resource_name": "de_components",
            "file_name": "decompounder.txt",
        },
    }],
}

word_list_file 参数接受包含以下字段的对象：

字段	字段
type	资源类型。通过add_file_resource 注册的文件使用"remote" 。有关自托管部署中使用的"local" 变体，请参阅管理文件资源。
resource_name	文件在add_file_resource 注册时使用的名称。
file_name	注册资源的对象存储路径中的文件名部分（例如，如果资源是通过path="file/decompounder.txt" 注册的，则为"decompounder.txt" ）。

示例

在将分析器配置应用到 Collections 模式之前，请使用run_analyzer 方法验证其行为。

分析器配置

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

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"));
                }}
        )
);

// javascript

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

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

验证使用run_analyzer

from pymilvus import (
    MilvusClient,
)

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

# 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)

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("dampfschifffahrt brotbackautomat");

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{"dampfschifffahrt brotbackautomat"}
option := milvusclient.NewRunAnalyzerOption(texts).
    WithAnalyzerParams(string(bs))

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

# restful

预期输出

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