Whitespace

The whitespace tokenizer divides text into terms whenever there is a space between words.

Configuration

To configure an analyzer using the whitespace tokenizer, set tokenizer to whitespace in analyzer_params.

Python

python

analyzer_params = {
    "tokenizer": "whitespace",
}

Java

java

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

NodeJS

javascript

const analyzer_params = {
    "tokenizer": "whitespace"
};

Go

go

analyzerParams = map[string]any{"tokenizer": "whitespace"}

cURL

bash

# restful
analyzerParams='{
  "tokenizer": "whitespace"
}'

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "whitespace"}
};

The whitespace tokenizer can work in conjunction with one or more filters. For example, the following code defines an analyzer that uses the whitespace tokenizer and lowercase filter:

Python

python

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

Java

java

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

NodeJS

javascript

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

Go

go

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

cURL

bash

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

C++

c++

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

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": "whitespace",
    "filter": ["lowercase"]
}

Java

java

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

NodeJS

javascript

// javascript

Go

go

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

cURL

bash

# restful

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "whitespace"},
    {"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 Milvus vector database is built for scale!"

# 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;

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 Milvus vector database is built for scale!");

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

NodeJS

javascript

// javascript

Go

go

import (
    "context"
    "encoding/json"
    "fmt"

    "github.com/milvus-io/milvus/client/v2/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
}

bs, _ := json.Marshal(analyzerParams)
texts := []string{"The Milvus vector database is built for scale!"}
option := milvusclient.NewRunAnalyzerOption(texts).
    WithAnalyzerParams(string(bs))

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

cURL

bash

# restful

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 Milvus vector database is 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;
}

Expected output

sql

['the', 'milvus', 'vector', 'database', 'is', 'built', 'for', 'scale!']