English

Zilliz Cloud の english analyzer は、英語テキストを処理するために設計されており、tokenization と filtering に言語固有のルールを適用します。

定義

english analyzer は以下のコンポーネントを使用します。

• Tokenizer: standard tokenizer を使用して、テキストを個別の単語単位に分割します。

• Filters: 包括的なテキスト処理のために複数の filter を含みます。

  • lowercase: すべての token を小文字に変換し、大文字と小文字を区別しない検索を可能にします。

  • stemmer: より広い一致をサポートするために単語を語幹形に変換します（例: "running" は "run" になります）。

  • stop_words: 一般的な英語の stop words を削除し、テキスト内の重要な語に焦点を当てます。

english analyzer の機能は、次のカスタム analyzer 設定と同等です。

Python

python

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

Java

java

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_"));
                }}
        )
);

Go

go

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

Rust

rust

use serde_json::json;

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

C++

c++

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

NodeJS

javascript

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

cURL

bash

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

設定

english analyzer を field に適用するには、analyzer_params で type を english に設定し、必要に応じてオプションのパラメータを含めるだけです。

Python

python

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

Java

java

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "type": "english"
});

C++

c++

nlohmann::json analyzer_params = {
    {"type", "english"}
};

NodeJS

javascript

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

cURL

bash

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

english analyzer は次のオプションパラメータを受け入れます。

Parameter	Description
stop_words	stop words のリストを含む配列で、tokenization から削除されます。デフォルトは _english_ で、一般的な英語の stop words の組み込みセットです。

カスタム stop words を使用した設定例:

Python

python

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

Java

java

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "type": "english",
    "stop_words": ["a", "an", "the"]
});

C++

c++

nlohmann::json analyzer_params = {
    {"type", "english"},
    {"stop_words", {"a", "an", "the"}}
};

NodeJS

javascript

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

cURL

bash

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

After defining analyzer_params, you can apply them to a VARCHAR field when defining a コレクション スキーマ. This allows Zilliz Cloud to process the text in that field using the specified analyzer for efficient tokenization and filtering. For details, refer to Example use.

例

Before applying the analyzer configuration to your コレクション スキーマ, verify its behavior using the run_analyzer method.

Analyzer 設定

Python

python

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

Java

java

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "type": "english",
    "stop_words": ["a", "an", "the"]
});

C++

c++

nlohmann::json analyzer_params = {
    {"type", "english"},
    {"stop_words", {"a", "an", "the"}}
};

NodeJS

javascript

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

cURL

bash

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

run_analyzer を使用した検証

Python

python

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(
    uri="YOUR_CLUSTER_ENDPOINT",
    token="YOUR_CLUSTER_TOKEN"
)

# 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)

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.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

ConnectConfig config = ConnectConfig.builder()
        .uri("YOUR_CLUSTER_ENDPOINT")
        .token("YOUR_CLUSTER_TOKEN")
        .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();

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{"Milvus is a vector database built for scale!"}
option := milvusclient.NewRunAnalyzerOption(texts...).
    WithAnalyzerParams(analyzerParams)

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

for _, r := range result {
    for _, token := range r.Tokens {
        fmt.Println("English analyzer output:", token.Text)
    }
}

Rust

rust

use milvus::v2::error::Result;
use milvus::v2::prelude::*;

#[tokio::main]
async fn main() -> Result<()> {
    let config = ConnectConfig::new().uri("YOUR_CLUSTER_ENDPOINT").token("YOUR_CLUSTER_TOKEN");
    let client = ClientV2::new(&config).await?;

    let analyzer_params = serde_json::json!({
        "type": "english",
        "stop_words": ["a", "an", "the"]
    });

    let response = client
        .run_analyzer(
            RunAnalyzerRequest::builder()
                .texts(["Milvus is a vector database built for scale!"])
                .analyzer_params(analyzer_params)
                .build()?,
        )
        .await?;

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

C++

c++

#include "milvus/MilvusClientV2.h"
#include <iostream>
#include <string>

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

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

std::string text = "Milvus is a vector database built for scale!";
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',
  token: 'YOUR_CLUSTER_TOKEN',
});

const sample_text = 'Milvus is a vector database built for scale!';
const result = await client.runAnalyzer({
  text: sample_text,
  analyzer_params,
});
const tokens = result.results.flatMap(r => r.tokens.map(t => t.token));
console.log('English 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": "{\"type\": \"english\", \"stop_words\": [\"a\", \"an\", \"the\"]}",
    "text": ["Milvus is a vector database built for scale!"]
  }' 

期待される出力

python

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