Cncharonly

The cncharonly filter removes tokens that contain any non-Chinese characters. This filter is useful when you want to focus solely on Chinese text, filtering out any tokens that contain other scripts, numbers, or symbols.

Configuration

The cncharonly 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": ["cncharonly"],
}

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("cncharonly"));

Go

go

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

Rust

rust

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

C++

cpp

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

NodeJS

javascript

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

CSharp

csharp

using System.Collections.Generic;

var analyzerParams = new Dictionary<string, object>
{
    ["tokenizer"] = "jieba",
    ["filter"] = new[] { "cncharonly" }
};

cURL

bash

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

The cncharonly 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": ["cncharonly"],
}

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("cncharonly"));

Go

go

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

Rust

rust

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

C++

cpp

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

NodeJS

javascript

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

CSharp

csharp

using System.Collections.Generic;

var analyzerParams = new Dictionary<string, object>
{
    ["tokenizer"] = "jieba",
    ["filter"] = new[] { "cncharonly" }
};

cURL

bash

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

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 java.util.*;
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 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"
)

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 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
}

for _, r := range result {
    for _, token := range r.Tokens {
        fmt.Println("Analyzer output:", token.Text)
    }
}

Rust

rust

use milvus::v2::error::Result;
use milvus::v2::prelude::*;

let config = ConnectConfig::new().uri("YOUR_CLUSTER_ENDPOINT").token("YOUR_CLUSTER_TOKEN");
let client = ClientV2::new(&config).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。";
let result = client
    .run_analyzer(
        RunAnalyzerRequest::builder()
            .texts(vec![sample_text])
            .analyzer_params(analyzer_params)
            .build()?,
    )
    .await?;

println!("Analyzer output: {:?}", result);

C++

cpp

#include "milvus/MilvusClientV2.h"
#include <iostream>
#include <string>

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
});
console.log("Analyzer output:", result);

CSharp

csharp

using Milvus.Client.V2;
using Milvus.Client.V2.Requests.Utility;
using Milvus.Client.V2.Responses.Utility;
using Milvus.Client.V2.Types;

var client = new MilvusClientV2(new ConnectConfig
{
    Uri = "YOUR_CLUSTER_ENDPOINT",
    ApiKey = "YOUR_CLUSTER_TOKEN"
});
await client.ConnectAsync();

// Sample text to analyze
var sampleText = "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
RunAnalyzerResp result = await client.RunAnalyzerAsync(new RunAnalyzerReq
{
    AnalyzerParams = analyzerParams,
    Texts = new[] { sampleText }
});
Console.WriteLine("Analyzer output: " + string.Join(", ", result.Results.SelectMany(r => r.Tokens).Select(t => t.Token)));

cURL

bash

export CLUSTER_ENDPOINT="YOUR_CLUSTER_ENDPOINT"
export TOKEN="YOUR_CLUSTER_TOKEN"

curl --request POST \
--url "${CLUSTER_ENDPOINT}/v2/vectordb/common/run_analyzer" \
--header "Authorization: Bearer ${TOKEN}" \
--header "Content-Type: application/json" \
--header "Request-Timeout: 10" \
-d '{
    "text": ["Milvus 是 LF AI & Data Foundation 下的一个开源项目，以 Apache 2.0 许可发布。"],
    "analyzerParams": "{\"tokenizer\": \"jieba\", \"filter\": [\"cncharonly\"]}"
}'

Expected output

plaintext

['是', '下', '的', '一个', '开源', '项目', '以', '许可', '发布']