Stemmer

stemmer 过滤器将单词简化为其基本或根形式（称为词干提取），使得匹配不同变化形式中具有相似意义的单词变得更加容易。stemmer 过滤器支持多种语言，允许在各种语言环境中有效地进行搜索和索引。

配置

stemmer 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": "stemmer" 并将 language 参数设置为您需要的值的方式来指定。

Python

python

analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "stemmer", # Specifies the filter type as stemmer
        "language": "english", # Sets the language for stemming to English
    }],
}

Java

java

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "tokenizer": "standard",
    "filter": [
        { "type": "stemmer", "language": "english" }
    ]
});

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "standard"},
    {"filter", {
        {
            {"type", "stemmer"},
            {"language", "english"}
        }
    }}
};

NodeJS

javascript

const analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "stemmer", // Specifies the filter type as stemmer
        "language": "english",
    }],
};

cURL

bash

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

stemmer 过滤器接受以下可选参数。

参数	描述
language	指定词干提取过程的语言。支持的语言包括："arabic", "danish", "dutch", "english", "finnish", "french", "german", "greek", "hungarian", "italian", "norwegian", "portuguese", "romanian", "russian", "spanish", "swedish", "tamil", "turkish"

stemmer 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。

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

python

analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "stemmer", # Specifies the filter type as stemmer
        "language": "english", # Sets the language for stemming to English
    }],
}

Java

java

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "tokenizer": "standard",
    "filter": [
        { "type": "stemmer", "language": "english" }
    ]
});

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "standard"},
    {"filter", {
        {
            {"type", "stemmer"},
            {"language", "english"}
        }
    }}
};

NodeJS

javascript

const analyzer_params = {
    "tokenizer": "standard",
    "filter":[{
        "type": "stemmer", // Specifies the filter type as stemmer
        "language": "english",
    }],
};

cURL

bash

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

使用 run_analyzer 验证效果

Python

python

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(uri="YOUR_CLUSTER_ENDPOINT")

# Sample text to analyze
sample_text = "running runs looked ran runner"

# Run the standard analyzer with the defined configuration
result = client.run_analyzer(sample_text, analyzer_params)
print("Standard analyzer output:", result)

Java

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;

import java.util.ArrayList;
import java.util.List;

ConnectConfig config = ConnectConfig.builder()
        .uri("YOUR_CLUSTER_ENDPOINT")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

List<String> texts = new ArrayList<>();
texts.add("running runs looked ran runner");

RunAnalyzerResp resp = client.runAnalyzer(RunAnalyzerReq.builder()
        .texts(texts)
        .analyzerParams(analyzerParams)
        .build());
List<RunAnalyzerResp.AnalyzerResult> results = resp.getResults();

Go

go

import (
    "context"
    "fmt"

    "github.com/milvus-io/milvus/client/v3/milvusclient"
)

client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
    Address: "YOUR_CLUSTER_ENDPOINT",
    APIKey:  "YOUR_CLUSTER_TOKEN",
})
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

texts := []string{"running runs looked ran runner"}
option := milvusclient.NewRunAnalyzerOption(texts...).
    WithAnalyzerParams(analyzerParams)

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

Rust

rust

use milvus::v2::prelude::*;

let response = client
    .run_analyzer(
        RunAnalyzerRequest::builder()
            .texts(["running runs looked ran runner"])
            .analyzer_params(analyzer_params)
            .build()?,
    )
    .await?;

for result in response.results() {
    for token in result.get_tokens() {
        println!("Standard analyzer output: {}", token.get_text());
    }
}

C++

c++

#include "milvus/MilvusClientV2.h"

auto client = milvus::MilvusClientV2::Create();

milvus::ConnectParam connect_param{"YOUR_CLUSTER_ENDPOINT"};
auto status = client->Connect(connect_param);
if (!status.IsOk()) {
    std::cout << status.Message() << std::endl;
}

std::string text = "running runs looked ran runner";
auto request = milvus::RunAnalyzerRequest()
                       .AddText(text)
                       .WithAnalyzerParams(analyzer_params);

milvus::RunAnalyzerResponse response;
status = client->RunAnalyzer(request, response);
if (!status.IsOk()) {
    std::cout << status.Message() << std::endl;
}

NodeJS

javascript

import { MilvusClient } from '@zilliz/milvus2-sdk-node';

const client = new MilvusClient({
  address: 'YOUR_CLUSTER_ENDPOINT',
});

const sample_text = 'running runs looked ran runner';
const result = await client.runAnalyzer({
  text: sample_text,
  analyzer_params,
});
const tokens = result.results.flatMap(r => r.tokens.map(t => t.token));
console.log('Standard analyzer output:', tokens);

cURL

bash

curl --request POST \
  --url "YOUR_CLUSTER_ENDPOINT/v2/vectordb/common/run_analyzer" \
  --header "Authorization: Bearer YOUR_CLUSTER_TOKEN" \
  --header "Content-Type: application/json" \
  --data-raw '{
    "analyzerParams": "{\"tokenizer\": \"standard\", \"filter\": [{\"type\": \"stemmer\", \"language\": \"english\"}]}",
    "text": ["running runs looked ran runner"]
  }' 

预期结果

python

['run', 'run', 'look', 'ran', 'runner']