Jieba

Jieba 分词器通过将中文文本拆分为其组成的单词来处理文本。

说明

jieba 分词器在输出的分词结果中会将标点符号作为独立的词元予以保留。例如："你好！世界。" 的分词结果为 ["你好", "！", "世界", "。"]。如果需要在分词结果中去除标点符号词元，需要使用 removepunct 过滤器。

配置

在 Milvus 中，jieba 分词器有两种使用方法：一种为简单配置；另一种为自定义配置。

简单配置

使用简单配置时，您只需要将 tokenizer 设置为 "jieba"。例如

python
# Simple configuration: only specifying the tokenizer name
analyzer_params = {
    "tokenizer": "jieba",  # Use the default settings: dict=["_default_"], mode="search", hmm=True
}

java

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

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

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

#[tokio::main]
async fn main() -> Result<()> {
    let analyzer_params = serde_json::json!({"tokenizer": "jieba"});

    Ok(())
}

c++
nlohmann::json analyzer_params = {
    {"tokenizer", "jieba"}
};

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

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

上述简单配置与下方示例中的配置等效。

python
# Custom configuration equivalent to the simple configuration above
analyzer_params = {
    "tokenizer": {                 # Tokenizer configuration
        "type": "jieba",           # Tokenizer type, fixed as "jieba"
        "dict": ["_default_"],     # Use the default dictionary
        "mode": "search",          # Use search mode for improved recall (see mode details below)
        "hmm": True                # Enable HMM for probabilistic segmentation
    }
}

java
Map<String, Object> analyzerParams = new HashMap<>();
analyzerParams.put("tokenizer", new HashMap<String, Object>() {{
  put("type", "jieba");
  put("dict", Collections.singletonList("_default_"));
  put("mode", "search");
  put("hmm", true);
}});

go
analyzerParams := map[string]any{
  "tokenizer": map[string]any{
    "type": "jieba",
    "dict": []any{"_default_"},
    "mode": "search",
    "hmm":  true,
  },
}

rust
    let analyzer_params = serde_json::json!({
        "tokenizer": {
            "type": "jieba",
            "dict": ["_default_"],
            "mode": "search",
            "hmm": true
        }
    });

c++
nlohmann::json analyzer_params = {
    {"tokenizer", {
        {"type", "jieba"},
        {"dict", {"_default_"}},
        {"mode", "search"},
        {"hmm", true}
    }}
};

javascript
const analyzer_params = {
  tokenizer: {
    type: "jieba",
    dict: ["_default_"],
    mode: "search",
    hmm: true,
  },
};

bash
# restful
export analyzerParams='{
  "tokenizer": {
    "type": "jieba",
    "dict": ["_default_"],
    "mode": "search",
    "hmm": true
  }
}'

关于 Analyzer 参数的更多配置，可以参考自定义配置。

自定义配置

为了更好地控制 Analyzer 参数，您可以自定义相关参数。例如，您可以参考如下示例为 Analyzer 提供自定义字典、选择文本切分方式，并选择是否开启隐式马尔科夫模型（HMM）等。

python
# Custom configuration with user-defined settings
analyzer_params = {
    "tokenizer": {
        "type": "jieba",           # Fixed tokenizer type
        "dict": ["customDictionary"],  # Custom dictionary list; replace with your own terms
        "mode": "exact",           # Use exact mode (non-overlapping tokens)
        "hmm": False               # Disable HMM; unmatched text will be split into individual characters
    }
}

java
Map<String, Object> analyzerParams = new HashMap<>();                                                                          
analyzerParams.put("tokenizer", new HashMap<String, Object>() {{
  put("type", "jieba");                                                                                                      
  put("dict", Arrays.asList("customDictionary"));             
  put("mode", "exact");
  put("hmm", false);
}});

go
analyzerParams := map[string]interface{}{
  "tokenizer": map[string]interface{}{
      "type": "jieba",
      "dict": []string{"customDictionary"},
      "mode": "exact",
      "hmm":  false,
  },
}

rust
    let analyzer_params = serde_json::json!({
        "tokenizer": {
            "type": "jieba",
            "dict": ["customDictionary"],
            "mode": "exact",
            "hmm": false
        }
    });

c++
nlohmann::json analyzerParams = {                                                                                              
  {"tokenizer", {                          
      {"type", "jieba"},                                                                                                     
      {"dict", {"customDictionary"}},                         
      {"mode", "exact"},                                                                                                     
      {"hmm", false}                                          
  }}
};

javascript
const analyzer_params = {
  tokenizer: {
    type: "jieba",
    dict: ["customDictionary"],
    mode: "exact",
    hmm: false,
  },
};

bash
# restful
export analyzerParams='{
  "tokenizer": {
    "type": "jieba",
    "dict": ["customDictionary"],
    "mode": "exact",
    "hmm": false
  }
}'

参数名称	参数描述	默认值
`type`	分词器类型，在使用 `jieba` 分词器时，该值为 `jieba`。	`"jieba"`
`dict`	Analyzer 在分析文本时可以参考的词汇表，以字典的形式提供。内置的字典包括： `"default"`: 加载文本分析引擎内置的简单中文字典。更多详情，可以参考 dict.txt。 `"extend_default"`: 加载上述简单中文字典以及繁体中文的相关内容。更多详情，可以参考 dict.txt.big。您也可以在引用内置字典的同时，添加任意长度的自定义字典。例如 `["default", "结巴分词器"]`。	`["default"]`
`mode`	文本切分方式。取值范围如下： `"exact"`: 尝试以最精确的方式对句子进行分段，使其满足文本分析的要求。 `"search"`: 在 `exact` 模式的基础上，对长词进行切分以便提升召回率。适用于搜索引擎场景下的分词操作。更多详情，可参考 Jieba GitHub 项目。	`"search"`
`hmm`	布尔型参数，指定是否开启隐式马尔科夫。当开启时，会对字典中未定义的单词进行可能地切分。	`true`

在定义了 analyzer_params 后，您可以在定义 Collection Schema 时将其应用到 VARCHAR 类型的字段上。Zilliz Cloud 将会根据 Analyzer 的设置对该字段的内容进行分词和过滤。更多详情，可参考使用示例。

使用示例

在完成 Analyzer 配置后，您可以使用 run_analyzer 方法来验证分词效果是否符合预期。

Analyzer 配置

python
analyzer_params = {
    "tokenizer": {
        "type": "jieba",
        "dict": ["结巴分词器"],
        "mode": "exact",
        "hmm": False
    }
}

java
Map<String, Object> analyzerParams = new HashMap<>();                                                                          
analyzerParams.put("tokenizer", new HashMap<String, Object>() {{
  put("type", "jieba");                                                                                                      
  put("dict", Arrays.asList("结巴分词器"));                   
  put("mode", "exact");
  put("hmm", false);
}});

go
analyzerParams := map[string]interface{}{
  "tokenizer": map[string]interface{}{
      "type": "jieba",
      "dict": []string{"结巴分词器"},
      "mode": "exact",
      "hmm":  false,
  },
}

rust
    let analyzer_params = serde_json::json!({
        "tokenizer": {
            "type": "jieba",
            "dict": ["结巴分词器"],
            "mode": "exact",
            "hmm": false
        }
    });

c++
nlohmann::json analyzerParams = {
  {"tokenizer", {
      {"type", "jieba"},
      {"dict", {"结巴分词器"}},
      {"mode", "exact"},
      {"hmm", false}
  }}
};

javascript
const analyzer_params = {
  tokenizer: {
    type: "jieba",
    dict: ["结巴分词器"],
    mode: "exact",
    hmm: false,
  },
};

bash
# restful
export analyzerParams='{
  "tokenizer": {
    "type": "jieba",
    "dict": ["结巴分词器"],
    "mode": "exact",
    "hmm": false
  }
}'

使用 run_analyzer 验证效果

python
from pymilvus import (
    MilvusClient,
)

client = MilvusClient(
    uri="YOUR_CLUSTER_ENDPOINT",
    token="YOUR_CLUSTER_TOKEN"
)

# Sample text to analyze
sample_text = "milvus结巴分词器中文测试"

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

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("milvus结巴分词器中文测试");

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

go
import (
    "context"
    "encoding/json"
    "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
}

bs, _ := json.Marshal(analyzerParams)
texts := []string{"milvus结巴分词器中文测试"}
option := milvusclient.NewRunAnalyzerOption(texts).
    WithAnalyzerParamsStr(string(bs))

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

rust
    let resp = client.run_analyzer(RunAnalyzerRequest::builder()
        .texts(vec!["milvus结巴分词器中文测试"])
        .analyzer_params(analyzer_params)
        .build()?).await?;
    println!("{:?}", resp.results());

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结巴分词器中文测试";
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;
}

javascript
const analyzer_params = {
  tokenizer: {
    type: "jieba",
    dict: ["结巴分词器"],
    mode: "exact",
    hmm: false,
  },
};

const result = await client.runAnalyzer({
  text: "milvus结巴分词器中文测试",
  analyzer_params,
});
console.log(result.results);

bash
curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/common/run" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--data '{
  "text": "milvus结巴分词器中文测试",
  "analyzerParams": {
    "tokenizer": {
      "type": "jieba",
      "dict": ["结巴分词器"],
      "mode": "exact",
      "hmm": false
    }
  }
}'

预期结果

python
['milvus', '结巴分词器', '中', '文', '测', '试']

配置​

简单配置​

自定义配置​

使用示例​

Analyzer 配置​

使用 run_analyzer 验证效果​

预期结果​

配置