ICU

ICU 分词器基于 Unicode 国际化组件（ICU）开源项目构建，该项目为软件国际化提供了关键工具。通过使用 ICU 的断词算法，分词器能够在世界上大多数语言中准确地将文本拆分为单词。

说明

ICU 分词器会在输出中将标点符号和空格保留为单独的 token。例如： "Привет! Как дела?" 会被分割为 ["Привет", "!", " ", "Как", " ", "дела", "?"]。 如果希望移除这些单独的标点符号 token，可以使用 removepunct 过滤器。

配置

要使用 icu 分词器，请在 analyzer_params 中将 tokenizer 设置为 icu。

Python

python

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

Java

java

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

Go

go

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

Rust

rust

use milvus::v2::prelude::*;
use serde_json::json;

let analyzer_params = json!({ "tokenizer": "icu" });

C++

c++

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

NodeJS

javascript

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

cURL

bash

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

ICU 分词器可以与一个或多个过滤器配合使用。例如，以下代码定义了一个使用 icu 分词器和 removepunct 过滤器的 Analyzer：

Python

python

analyzer_params = {
    "tokenizer": "icu",
    "filter": ["removepunct"]
}

Java

java

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

Go

go

analyzerParams = map[string]any{"tokenizer": "icu", "filter": []string{"removepunct"}}

Rust

rust

use milvus::v2::prelude::*;
use serde_json::json;

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

C++

c++

nlohmann::json analyzer_params = {
    {"tokenizer", "icu"},
    {"filter", {"removepunct"}}
};

NodeJS

javascript

const analyzer_params = {
    tokenizer: "icu",
    filter: ["removepunct"],
};

cURL

bash

# restful
analyzerParams='{
  "tokenizer": "icu",
  "filter": ["removepunct"]
}'

定义 analyzer_params 后，您可以在定义 Collection Schema 时将其应用于 VARCHAR 字段。这使得 Zilliz Cloud 能够使用指定的分析器处理该字段中的文本，以实现高效的分词和过滤。更多信息，请参阅使用示例。

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

python

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

Java

java

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

Go

go

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

Rust

rust

use milvus::v2::prelude::*;
use serde_json::json;

let analyzer_params = json!({ "tokenizer": "icu" });

C++

c++

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

NodeJS

javascript

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

cURL

bash

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

使用 run_analyzer 验证效果

Python

python

from pymilvus import (
    MilvusClient,
)

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

# Sample text to analyze
sample_text = "Привет! Как дела?"

# 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("Привет! Как дела?");

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"
)

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{"Привет! Как дела?"}
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 analyzer_params = json!({ "tokenizer": "icu" });
let result = client
    .run_analyzer(
        RunAnalyzerRequest::builder()
            .texts(vec!["Привет! Как дела?"])
            .analyzer_params(analyzer_params)
            .build()?,
    )
    .await?;

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 = "Привет! Как дела?";
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

const sample_text = "Привет! Как дела?";

// Run the icu analyzer with the defined configuration
const result = await client.runAnalyzer({
    text: sample_text,
    analyzer_params,
});
console.log("ICU analyzer output:", result);

cURL

bash

# restful
curl --request POST \
     --url "YOUR_CLUSTER_ENDPOINT/v2/vectordb/common/run_analyzer" \
     --header "Authorization: Bearer YOUR_CLUSTER_TOKEN" \
     --header "Content-Type: application/json" \
     -d '{
        "text": ["Привет! Как дела?"],
        "analyzerParams": "{\"tokenizer\": \"icu\"}"
     }'

预期输出

plaintext

['Привет', '!', ' ', 'Как', ' ', 'дела', '?']