英文

Milvus 中的english 分析器專為處理英文文字而設計，並應用特定語言的符號化和過濾規則。

定義

english 分析器使用下列元件：

• 標記器：使用standard tokenizer將文字分割為離散的單字單位。

• 過濾器：包含多種篩選器，可進行全面的文字處理：

  • lowercase:將所有標記轉換為小寫，以便進行不區分大小寫的搜尋。

  • stemmer:將字詞縮減為字根形式，以支援更廣泛的匹配 (例如，「running」變為「run」)。

  • stop_words:移除常見的英文停止詞，以聚焦於文字中的關鍵詞。

english 分析器的功能等同於下列自訂分析器配置：

analyzer_params = {
        "tokenizer": "standard",
        "filter": [
                "lowercase",
                {
                        "type": "stemmer",
                        "language": "english"
                }, {
                        "type": "stop",
                        "stop_words": "_english_"
                }
        ]
}

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

const analyzer_params = {
    "type": "standard", // Specifies the standard analyzer type
    "stop_words", ["of"] // Optional: List of words to exclude from tokenization
}

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

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

配置

要將english 分析器套用至欄位，只要在analyzer_params 中將type 設定為english ，並視需要加入可選參數即可。

analyzer_params = {
    "type": "english",
}

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

const analyzer_params = {
    "type": "english",
}

analyzerParams = map[string]any{"type": "english"}

# restful
analyzerParams='{
  "type": "english"
}'

english 分析器接受下列可選參數：

參數	說明
stop_words	一個包含停止詞清單的陣列，這些停止詞將從標記化中移除。預設為_english_ ，這是一套內建的常見英文停止詞。

自訂停止詞的配置範例：

analyzer_params = {
    "type": "english",
    "stop_words": ["a", "an", "the"]
}

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("type", "english");
analyzerParams.put("stop_words", Arrays.asList("a", "an", "the"));

const analyzer_params = {
    "type": "english",
    "stop_words": ["a", "an", "the"]
}

analyzerParams = map[string]any{"type": "english", "stop_words": []string{"a", "an", "the"}}

# restful
analyzerParams='{
  "type": "english",
  "stop_words": [
    "a",
    "an",
    "the"
  ]
}'

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 使用指定的分析器處理該欄位中的文字，以進行有效的標記化和過濾。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 = {
    "type": "english",
    "stop_words": ["a", "an", "the"]
}

Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("type", "english");
analyzerParams.put("stop_words", Arrays.asList("a", "an", "the"));

// javascript

analyzerParams = map[string]any{"type": "english", "stop_words": []string{"a", "an", "the"}}

# restful
analyzerParams='{
  "type": "english",
  "stop_words": [
    "a",
    "an",
    "the"
  ]
}'

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 = "Milvus is a vector database built for scale!"

# Run the standard analyzer with the defined configuration
result = client.run_analyzer(sample_text, analyzer_params)
print("English 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("Milvus is a vector database 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{"Milvus is a vector database 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

English analyzer output: ['milvus', 'vector', 'databas', 'built', 'scale']