Jieba

Contact Sales to Enable BYOC

The jieba tokenizer processes Chinese text by breaking it down into its component words.

Configuration

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

Python

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

Java

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

NodeJS

const analyzer_params = {
    "tokenizer": "jieba",
};

Go

// go

cURL

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

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

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

Java

// java

NodeJS

// javascript

Go

// go

cURL

# restful

Verification using run_analyzer:

Python

# 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 = MilvusClient.run_analyzer(sample_text, analyzer_params)
print(result)

Java

// java

NodeJS

// javascript

Go

// go

cURL

# restful

Expected 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", "！"]