Cnalphanumonly

The cnalphanumonly filter removes tokens that contain any characters other than Chinese characters, English letters, or digits.

Configuration

The cnalphanumonly filter is built into Zilliz Cloud. To use it, simply specify its name in the filter section within analyzer_params.

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

let analyzer_params = serde_json::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"
  ]
}'

The cnalphanumonly filter operates on the terms generated by the tokenizer, so it must be used in combination with a tokenizer. For a list of tokenizers available in Zilliz Cloud, refer to Jieba and its sibling pages.

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

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

let analyzer_params = serde_json::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"
  ]
}' 

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 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。"

# Run the jieba tokenizer with the defined configuration
result = client.run_analyzer(sample_text, analyzer_params)
print("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;
import java.util.*;

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 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。");

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{"Milvus 是 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。"}
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::*;

let client = ClientV2::new(&ConnectConfig::new().uri("YOUR_CLUSTER_ENDPOINT").token("YOUR_CLUSTER_TOKEN")).await?;

let sample_text = "Milvus 是 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。";
client
    .run_analyzer(
        RunAnalyzerRequest::builder()
            .texts([sample_text])
            .analyzer_params(analyzer_params.clone())
            .build()?,
    )
    .await?;

C++

c++

#include <iostream>
#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 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。";
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 client = new MilvusClient({
    address: "YOUR_CLUSTER_ENDPOINT",
    token: "YOUR_CLUSTER_TOKEN"
});

// Sample text to analyze
const sample_text = "Milvus 是 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。";

// Run the jieba tokenizer with the defined configuration
const result = await client.runAnalyzer({
    text: sample_text,
    analyzer_params: analyzer_params
});

cURL

bash

# restful
export MILVUS_HOST="YOUR_CLUSTER_ENDPOINT"
export SAMPLE_TEXT="Milvus 是 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。"
curl -X POST "http://${MILVUS_HOST}/v2/vectordb/common/run_analyzer" \
  -H "Content-Type: application/json" \
  -H "Request-Timeout: 10" \
  -d '{
    "text": ["'"${SAMPLE_TEXT}"'"],
    "analyzerParams": "{\"tokenizer\":\"jieba\",\"filter\":[\"cnalphanumonly\"]}"
  }' 

Expected output

python

['Milvus', '是', 'LF', 'AI', 'Data', 'Foundation', '下', '的', '一个', '开源', '项目', '以', 'Apache', '2.0', '许可', '发布']