仅字母

alphanumonly 过滤器删除包含非 ASCII 字符的标记，只保留字母数字术语。该过滤器适用于处理只有基本字母和数字的文本，不包括任何特殊字符或符号。

配置

alphanumonly 过滤器内置在 Milvus 中。要使用它，只需在analyzer_params 中的filter 部分指定其名称即可。

Python

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

Java

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

NodeJS

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

Go

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

cURL

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

alphanumonly 过滤器对标记符生成的术语进行操作，因此必须与标记符结合使用。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 Collection 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。有关详情，请参阅示例使用。

示例

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

分析器配置

Python

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

Java

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

NodeJS

// javascript

Go

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

cURL

# restful

验证使用run_analyzerCompatible with Milvus 2.5.11+

Python

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)

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("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();

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:  "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
}

cURL

# restful

预期输出

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