僅字母

alphanumonly 過濾器會移除包含非 ASCII 字元的標記，只保留字母數字詞。此過濾器適用於處理只有基本字母和數字相關的文字，排除任何特殊字符或符號。

設定

alphanumonly 過濾器內建於 Milvus。要使用它，只需在analyzer_params 中的filter 部分指定其名稱即可。

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

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

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

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

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

alphanumonly 過濾器會在 tokenizer 產生的詞彙上運作，因此必須與 tokenizer 結合使用。如需 Milvus 中可用的 tokenizer 清單，請參考Standard Tokenizer及其同屬頁面。

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。這允許 Milvus 使用指定的分析器來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 = {
    "tokenizer": "standard",
    "filter": ["alphanumonly"],
}

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

// javascript

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

# restful

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 2.0 @ Scale! #AI #Vector_Databasé"

# 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("Milvus 2.0 @ Scale! #AI #Vector_Databasé");

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 2.0 @ Scale! #AI #Vector_Databasé"}
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

['Milvus', '2', '0', 'Scale', 'AI', 'Vector']