Lowercase

lowercase フィルターは、トークナイザーによって生成された用語を小文字に変換し、検索で大文字と小文字が区別されないようにします。たとえば、["High", "Performance", "Vector", "Database"] を ["high", "performance", "vector", "database"] に変換できます。

設定

lowercase フィルターは Zilliz Cloud に組み込まれています。使用するには、analyzer_params 内の filter セクションにその名前を指定するだけです。

Python

python

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

Java

java

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "tokenizer": "standard",
    "filter": ["lowercase"]
});

C++

c++

#include <milvus/thirdparty/nlohmann/json.hpp>

nlohmann::json analyzer_params = {
    {"tokenizer", "standard"},
    {"filter", {"lowercase"}}
};

NodeJS

javascript

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

CSharp

csharp

using System.Collections.Generic;

Dictionary<string, object> analyzerParams = new()
{
    ["tokenizer"] = "standard",
    ["filter"] = new List<object> { "lowercase" }
};

cURL

bash

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

lowercase フィルターはトークナイザーによって生成された用語に対して動作するため、トークナイザーと組み合わせて使用する必要があります。

analyzer_params を定義した後、コレクションスキーマを定義する際に、それらを VARCHAR フィールドに適用できます。これにより、Zilliz Cloud は指定されたアナライザーを使用してそのフィールド内のテキストを処理し、効率的なトークン化とフィルタリングを実行できます。詳細については、使用例 を参照してください。

例

アナライザー構成をコレクションスキーマに適用する前に、run_analyzer メソッドを使用してその動作を確認してください。

アナライザー構成

Python

python

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

Java

java

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "tokenizer": "standard",
    "filter": ["lowercase"]
});

C++

c++

#include <milvus/thirdparty/nlohmann/json.hpp>

nlohmann::json analyzer_params = {
    {"tokenizer", "standard"},
    {"filter", {"lowercase"}}
};

NodeJS

javascript

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

CSharp

csharp

using System.Collections.Generic;

Dictionary<string, object> analyzerParams = new()
{
    ["tokenizer"] = "standard",
    ["filter"] = new List<object> { "lowercase" }
};

cURL

bash

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

run_analyzer を使用した確認

Python

python

from pymilvus import (
    MilvusClient,
)

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

# Sample text to analyze
sample_text = "The Lowercase Filter Ensures Uniformity In Text Processing."

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

Java

java

import java.util.*;
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("YOUR_CLUSTER_ENDPOINT")
        .token("YOUR_CLUSTER_TOKEN")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

List<String> texts = new ArrayList<>();
texts.add("The Lowercase Filter Ensures Uniformity In Text Processing.");

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"
)

ctx := context.Background()

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{"The Lowercase Filter Ensures Uniformity In Text Processing."}
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(token.Text)
    }
}

Rust

rust

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

let config = ConnectConfig::new().uri("YOUR_CLUSTER_ENDPOINT").token("YOUR_CLUSTER_TOKEN");
let client = ClientV2::new(&config).await?;

let response = client
    .run_analyzer(
        RunAnalyzerRequest::builder()
            .texts(["The Lowercase Filter Ensures Uniformity In Text Processing."])
            .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"
#include <string>
#include <iostream>

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 = "The Lowercase Filter Ensures Uniformity In Text Processing.";
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 = 'The Lowercase Filter Ensures Uniformity In Text Processing.';
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);

CSharp

csharp

using System;
using Milvus.Client.V2;
using Milvus.Client.V2.Requests.Utility;
using Milvus.Client.V2.Responses.Utility;
using Milvus.Client.V2.Types;

MilvusClientV2 client = new(new ConnectConfig
{
    Uri = "YOUR_CLUSTER_ENDPOINT",
    ApiKey = "YOUR_CLUSTER_TOKEN"
});

// Sample text to analyze
string sampleText = "The Lowercase Filter Ensures Uniformity In Text Processing.";

// Run the standard analyzer with the defined configuration
RunAnalyzerResp result = await client.RunAnalyzerAsync(new RunAnalyzerReq
{
    AnalyzerParams = analyzerParams,
    Texts = [sampleText]
});

foreach (AnalyzerResult r in result.Results)
{
    foreach (AnalyzerToken t in r.Tokens)
    {
        Console.WriteLine($"Standard analyzer output: {t.Token}");
    }
}

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\": [\"lowercase\"]}",
    "text": ["The Lowercase Filter Ensures Uniformity In Text Processing."]
  }'

期待される出力

plaintext

['the', 'lowercase', 'filter', 'ensures', 'uniformity', 'in', 'text', 'processing']