Lowercase

The lowercase filter converts terms generated by a tokenizer to lowercase, making searches case-insensitive. For example, it can convert ["High", "Performance", "Vector", "Database"] to ["high", "performance", "vector", "database"].

Configuration

The lowercase filter is built into Zilliz Cloud. To use it, simply specify its name in the filter section within analyzer_params.

Python

python

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

Java

java

import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

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++

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

NodeJS

javascript

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

cURL

bash

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

The lowercase filter operates on the terms generated by the tokenizer, so it must be used in combination with a tokenizer.

After defining analyzer_params, you can apply them to a VARCHAR field when defining a collection schema. 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.

Examples

Before applying the analyzer configuration to your collection schema, verify its behavior using the run_analyzer method.

Analyzer configuration

Python

python

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

Java

java

import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

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++

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

NodeJS

javascript

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

cURL

bash

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

Verification using run_analyzer

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 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")
        .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"
)

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
}

Rust

rust

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

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"

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',
});

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);

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."]
  }' 

Expected output

python

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