Chinese

The chinese analyzer is designed specifically to handle Chinese text, providing effective segmentation and tokenization.

Definition

The chinese analyzer consists of:

• Tokenizer: Uses the jieba tokenizer to segment Chinese text into tokens based on vocabulary and context. For more information, refer to Jieba.

• Filter: Uses the cnalphanumonly filter to remove tokens that contain any non-Chinese characters. For more information, refer to Cnalphanumonly.

The functionality of the chinese analyzer is equivalent to the following custom analyzer configuration:

analyzer_params = {
    "tokenizer": "jieba",
    "filter": ["cnalphanumonly"]
}

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

const analyzer_params = {
    "tokenizer": "jieba",
    "filter": ["cnalphanumonly"]
};

analyzerParams = map[string]any{"tokenizer": "jieba", "filter": []any{"cnalphanumonly"}}

# restful
analyzerParams='{
  "tokenizer": "jieba",
  "filter": [
    "cnalphanumonly"
  ]
}'

Configuration

To apply the chinese analyzer to a field, simply set type to chinese in analyzer_params.

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

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

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

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

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

Examples

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

Analyzer configuration

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

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

// javascript

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

# restful

Verification using run_analyzerCompatible with Milvus 2.5.11+

from pymilvus import (
    MilvusClient,
)

client = MilvusClient(uri="http://localhost:19530")

# Sample text to analyze
sample_text = "Milvus 是一个高性能、可扩展的向量数据库！"

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

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")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

List<String> texts = new ArrayList<>();
texts.add("Milvus 是一个高性能、可扩展的向量数据库！");

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

// javascript

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

    "github.com/milvus-io/milvus/client/v2/milvusclient"
)

client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
    Address: "localhost:19530",
    APIKey:  "root:Milvus",
})
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

bs, _ := json.Marshal(analyzerParams)
texts := []string{"Milvus 是一个高性能、可扩展的向量数据库！"}
option := milvusclient.NewRunAnalyzerOption(texts).
    WithAnalyzerParams(string(bs))

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

# restful

Expected output

Chinese analyzer output: ['Milvus', '是', '一个', '高性', '性能', '高性能', '可', '扩展', '的', '向量', '数据', '据库', '数据库']