Minuscules

Le filtre « lowercase » convertit en minuscules les termes générés par un tokenizer, ce qui rend les recherches insensibles à la casse. Par exemple, il peut convertir « ["High", "Performance", "Vector", "Database"] » en « ["high", "performance", "vector", "database"] ».

Configuration

Le filtre « lowercase » est intégré à Milvus. Pour l’utiliser, il suffit d’indiquer son nom dans la section « filter » du fichier « analyzer_params ».

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

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

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

use serde_json::json;

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

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

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

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

using System.Collections.Generic;

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

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

Le filtre « lowercase » agit sur les termes générés par le tokenizer ; il doit donc être utilisé en combinaison avec un tokenizer.

Une fois les filtres d’ analyzer_params s définis, vous pouvez les appliquer à un champ « VARCHAR » lors de la définition d’un schéma de collection. Cela permet à Milvus de traiter le texte de ce champ à l’aide de l’analyseur spécifié, pour une tokenisation et un filtrage efficaces. Pour plus de détails, consultez la section « Exemple d’utilisation ».

Exemples

Avant d’appliquer la configuration de l’analyseur à votre schéma de collection, vérifiez son comportement à l’aide de la méthode ` run_analyzer `.

Configuration de l’analyseur

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

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

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

use serde_json::json;

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

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

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

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

using System.Collections.Generic;

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

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

Vérification à l’aide de run_analyzer

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(
    uri="http://localhost:19530",
    token="root:Milvus"
)

# 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)

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("http://localhost:19530")
        .token("root:Milvus")
        .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();

import (
    "context"
    "fmt"

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

ctx := context.Background()

client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
    Address: "http://localhost:19530",
    APIKey:  "root:Milvus",
})
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)
    }
}

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

let config = ConnectConfig::new().uri("http://localhost:19530").token("root:Milvus");
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());
    }
}

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

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

milvus::ConnectParam connect_param{"http://localhost:19530", "root:Milvus"};
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;
}

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

const client = new MilvusClient({
  address: 'http://localhost:19530',
  token: "root:Milvus",
});

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);

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 = "http://localhost:19530",
    ApiKey = "root:Milvus"
});

// 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 --request POST \
  --url "http://localhost:19530/v2/vectordb/common/run_analyzer" \
  --header "Authorization: Bearer root:Milvus" \
  --header "Content-Type: application/json" \
  --data-raw '{
    "analyzerParams": "{\"tokenizer\": \"standard\", \"filter\": [\"lowercase\"]}",
    "text": ["The Lowercase Filter Ensures Uniformity In Text Processing."]
  }'

Résultat attendu

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