"pipelineHandlers": {
  "FileParserHandler": ["SplitTextHandler"],
  "SplitTextHandler": ["TextEmbeddingHandler"],
  "TextEmbeddingHandler": ["ImageEmbeddingHandler"],
  "ImageEmbeddingHandler": []
}

"embeddingModelCfg": {
  "modelVersion": "default"  // 向量表征模型版本
}

"chunkSplitter": {
  "chunkSize": 3072,        // 每个Chunk的最大长度
  "segmentSize": 300,        // Chunk内部分段的最大长度
  "overlapRatio": 0.1        // 相邻Chunk之间的重叠比例
}

"perRecordLimit": {
  "parseFileMaxCnt": 10,        // 最多解析的文件数
  "textEmbeddingMaxCnt": 50,     // 最多向量表征的文本段数
  "imageEmbeddingMaxCnt": 10     // 最多处理的图片数量
}

getKnowledgeProcessor → 获取加工对象
        ↓
   getStatus → 查询加工状态
        ↓
 数据变更/开库 → 自动触发加工

src/main/resources/rawfile/arkdata/knowledge/knowledge_schema.json

{
  "knowledgeSource": [{
    "version": 1,
    "dbName": "testmail_store.db",
    "tables": [{
      "tableName": "email",
      "referenceFields": ["id"],
      "knowledgeFields": [
        {
          "columnName": "subject",
          "type": ["Text"]
        },
        {
          "columnName": "content",
          "type": ["Text"]
        },
        {
          "columnName": "image_text",
          "type": ["Text"]
        },
        {
          "columnName": "attachment_names",
          "type": ["Text"]
        },
        {
          "columnName": "inline_files",
          "type": ["Json"],
          "parser": [
            {
              "type": "File",
              "path": "$[*].uri"
            }
          ]
        },
        {
          "columnName": "sender",
          "type": ["Scalar"],
          "description": "sender"
        },
        {
          "columnName": "receivers",
          "type": ["Scalar"],
          "description": "receivers"
        },
        {
          "columnName": "received_date",
          "type": ["Scalar"],
          "description": "received_date"
        }
      ],
      "pipelineHandlers": {
        "FileParserHandler": ["SplitTextHandler"],
        "SplitTextHandler": ["TextEmbeddingHandler"],
        "TextEmbeddingHandler": ["ImageEmbeddingHandler"],
        "ImageEmbeddingHandler": []
      }
    }],
    "knowledgeProcess": {
      "embeddingModelCfg": {
        "modelVersion": "default"
      },
      "chunkSplitter": {
        "chunkSize": 3072,
        "segmentSize": 300,
        "overlapRatio": 0.1
      },
      "perRecordLimit": {
        "parseFileMaxCnt": 10,
        "textEmbeddingMaxCnt": 50,
        "imageEmbeddingMaxCnt": 10
      }
    }
  }]
}

import { relationalStore } from '@kit.ArkData';

// 开库参数配置
const storeConfig: relationalStore.StoreConfig = {
  name: 'testmail_store.db',           // 必须与 schema 中 dbName 一致
  securityLevel: relationalStore.SecurityLevel.S3,
  enableSemanticIndex: true,            // 必须设为 true 才会触发知识加工
  tokenizer: relationalStore.Tokenizer.CUSTOM_TOKENIZER
};

// 建表语句（表名、列名必须与 schema 一致）
const createTableSql = `CREATE TABLE IF NOT EXISTS email(
  id integer primary key, 
  subject text, 
  content text, 
  image_text text, 
  attachment_names text, 
  inline_files text, 
  sender text, 
  receivers text, 
  received_date text
);`;

// 插入数据示例
const insertSql = `insert or replace into email VALUES(
  0, 
  'Subject of an email', 
  'Content of an email',
  'Convert image to text through OCR', 
  'attachment_name_1.txt',
  '[{"uri":"/data/storage/el2/base/haps/entry/files/capture_1.png"},{"uri":"/data/storage/el2/base/haps/entry/files/capture_2.jpeg"}]',
  'zhangsan(zhangsan@xxx.com)', 
  'lisi(lisi@xxx.com), wangwu(wangwu@xxx.com)', 
  'Convert time to timestamp'
);`;

import { relationalStore } from '@kit.ArkData';
import { knowledgeProcessor } from '@kit.DataAugmentationKit';
import { UIAbility, common } from '@kit.AbilityKit';

// 开库参数配置
const storeConfig: relationalStore.StoreConfig = {
  name: 'testmail_store.db',
  securityLevel: relationalStore.SecurityLevel.S3,
  enableSemanticIndex: true,
  tokenizer: relationalStore.Tokenizer.CUSTOM_TOKENIZER
};

// 知识加工配置
let knowledgeSourceConfig: knowledgeProcessor.KnowledgeSourceConfig = {
  rdbSource: storeConfig,
};

let knowledgeProcessorConfig: knowledgeProcessor.KnowledgeProcessorConfig = {
  sourceConfig: knowledgeSourceConfig,
};

// 获取知识加工状态
async function getKnowledgeProcessingStatus() {
  const context = AppStorage.get<common.UIAbilityContext>("Context") as common.UIAbilityContext;
  
  try {
    // 1. 获取知识加工对象
    const processor = await knowledgeProcessor.getKnowledgeProcessor(
      context, 
      knowledgeProcessorConfig
    );
    
    // 2. 获取知识加工状态
    const status: knowledgeProcessor.ProcessorStatus = await processor.getStatus();
    
    console.info(`知识加工状态: ${JSON.stringify(status)}`);
    return status;
  } catch (err) {
    console.error(`获取知识加工状态失败: ${err.message}, code: ${err.code}`);
    return undefined;
  }
}