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:

Notes

The built-in chinese analyzer does not emit Pinyin tokens. To match Chinese text with Pinyin query terms, use a custom analyzer with the jieba tokenizer and the Pinyin filter.

Python

python

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

Java

java

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

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

Go

go

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

Rust

rust

use serde_json::json;

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

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "jieba"},
    {"filter", {"cnalphanumonly"}}
};

NodeJS

javascript

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

cURL

bash

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

Configuration

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

Python

python

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

Java

java

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

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "type": "chinese"
});

C++

c++

nlohmann::json analyzer_params = {
    {"type", "chinese"}
};

NodeJS

javascript

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

cURL

bash

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

Notes

The chinese analyzer does not accept any optional parameters.

Examples

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

Analyzer configuration

Python

python

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

Java

java

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

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

Go

go

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

Rust

rust

use serde_json::json;

let analyzer_params = json!({
    "type": "chinese"
});

C++

c++

nlohmann::json analyzer_params = {
    {"type", "chinese"}
};

NodeJS

javascript

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

cURL

bash

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

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 = "Milvus 是一个高性能、可扩展的向量数据库！"

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

Java

java

import java.util.ArrayList;
import java.util.List;
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("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();

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{"Milvus 是一个高性能、可扩展的向量数据库！"}
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::*;
use serde_json::json;

let text = "Milvus 是一个高性能、可扩展的向量数据库！";

let response = client
    .run_analyzer(
        RunAnalyzerRequest::builder()
            .texts([text])
            .analyzer_params(json!({"type": "chinese"}))
            .build()?,
    )
    .await?;

for result in response.results() {
    for token in result.get_tokens() {
        println!("{}", 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 = "Milvus 是一个高性能、可扩展的向量数据库！";
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 sampleText = "Milvus 是一个高性能、可扩展的向量数据库！";

const client = new MilvusClient({
  address: "YOUR_CLUSTER_ENDPOINT",
});

const result = await client.runAnalyzer({
  analyzer_params: analyzerParams,
  text: sampleText,
});

cURL

bash

# restful
curl -X POST "YOUR_CLUSTER_ENDPOINT/v2/vectordb/common/run_analyzer" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_CLUSTER_TOKEN" \
  -d '{
    "analyzerParams": "{\"type\": \"chinese\"}",
    "text": ["Milvus 是一个高性能、可扩展的向量数据库！"]
  }'

Expected output

python

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']