4.6.3-website dataset (#532)

projects/app/src/pages/api/admin/initv46-2.ts

@@ -1,7 +1,7 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { PgClient } from '@fastgpt/service/common/pg';
 import {
   DatasetDataIndexTypeEnum,

projects/app/src/pages/api/admin/initv46-fix.ts

@@ -1,12 +1,9 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { PgClient } from '@fastgpt/service/common/pg';
-import {
-  DatasetDataIndexTypeEnum,
-  PgDatasetTableName
-} from '@fastgpt/global/core/dataset/constant';
+import { PgDatasetTableName } from '@fastgpt/global/core/dataset/constant';
 
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';

projects/app/src/pages/api/admin/initv46.ts

@@ -8,7 +8,7 @@ import {
 } from '@fastgpt/service/support/user/team/controller';
 import { MongoUser } from '@fastgpt/service/support/user/schema';
 import { UserModelSchema } from '@fastgpt/global/support/user/type';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
 import { PermissionTypeEnum } from '@fastgpt/global/support/permission/constant';
 import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';

projects/app/src/pages/api/admin/initv462-2.ts

@@ -1,7 +1,7 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { MongoApp } from '@fastgpt/service/core/app/schema';
 import { FlowNodeInputTypeEnum, FlowNodeTypeEnum } from '@fastgpt/global/core/module/node/constant';

projects/app/src/pages/api/admin/initv462.ts

@@ -1,7 +1,7 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { jsonRes } from '@fastgpt/service/common/response';
 import { connectToDatabase } from '@/service/mongo';
-import { delay } from '@/utils/tools';
+import { delay } from '@fastgpt/global/common/system/utils';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
 import { jiebaSplit } from '@/service/core/dataset/utils';
@@ -17,10 +17,13 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
 
     console.log(
       'total',
-      await MongoDatasetData.countDocuments({ fullTextToken: { $exists: false } })
+      await MongoDatasetData.countDocuments({
+        fullTextToken: { $exists: false },
+        updateTime: { $lt: new Date() }
+      })
     );
 
-    await initFullTextToken(limit);
+    await initFullTextToken(limit, new Date());
 
     jsonRes(res, {
       message: 'success'
@@ -34,9 +37,12 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
     });
   }
 }
-export async function initFullTextToken(limit = 50): Promise<any> {
+export async function initFullTextToken(limit = 50, endDate: Date): Promise<any> {
   try {
-    const dataList = await MongoDatasetData.find({ fullTextToken: { $exists: false } }, '_id q a')
+    const dataList = await MongoDatasetData.find(
+      { fullTextToken: { $exists: false }, updateTime: { $lt: endDate } },
+      '_id q a'
+    )
       .limit(limit)
       .lean();
     if (dataList.length === 0) return;
@@ -56,9 +62,9 @@ export async function initFullTextToken(limit = 50): Promise<any> {
 
     success += result.filter((item) => item.status === 'fulfilled').length;
     console.log(`success: ${success}`);
-    return initFullTextToken(limit);
+    return initFullTextToken(limit, endDate);
   } catch (error) {
     await delay(1000);
-    return initFullTextToken(limit);
+    return initFullTextToken(limit, endDate);
   }
 }

projects/app/src/pages/api/admin/initv463-2.ts

@@ -0,0 +1,62 @@
+import type { NextApiRequest, NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { connectToDatabase } from '@/service/mongo';
+import { delay } from '@fastgpt/global/common/system/utils';
+import { authCert } from '@fastgpt/service/support/permission/auth/common';
+import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
+import { jiebaSplit } from '@/service/core/dataset/utils';
+
+let success = 0;
+/* pg 中的数据搬到 mongo dataset.datas 中，并做映射 */
+export default async function handler(req: NextApiRequest, res: NextApiResponse) {
+  try {
+    const { limit = 50 } = req.body as { limit: number };
+    await authCert({ req, authRoot: true });
+    await connectToDatabase();
+    success = 0;
+
+    console.log('total', await MongoDatasetData.countDocuments({ inited: { $exists: false } }));
+
+    await initFullTextToken(limit);
+
+    jsonRes(res, {
+      message: 'success'
+    });
+  } catch (error) {
+    console.log(error);
+
+    jsonRes(res, {
+      code: 500,
+      error
+    });
+  }
+}
+export async function initFullTextToken(limit = 50): Promise<any> {
+  try {
+    const dataList = await MongoDatasetData.find({ inited: { $exists: false } }, '_id q a')
+      .limit(limit)
+      .lean();
+    if (dataList.length === 0) return;
+
+    const result = await Promise.allSettled(
+      dataList.map((item) => {
+        const text = item.q + (item.a || '');
+        const tokens = jiebaSplit({ text });
+
+        return MongoDatasetData.findByIdAndUpdate(item._id, {
+          $set: {
+            inited: true,
+            fullTextToken: tokens
+          }
+        });
+      })
+    );
+
+    success += result.filter((item) => item.status === 'fulfilled').length;
+    console.log(`success: ${success}`);
+    return initFullTextToken(limit);
+  } catch (error) {
+    await delay(1000);
+    return initFullTextToken(limit);
+  }
+}

projects/app/src/pages/api/admin/initv463.ts

@@ -4,7 +4,8 @@ import { connectToDatabase } from '@/service/mongo';
 import { authCert } from '@fastgpt/service/support/permission/auth/common';
 import { MongoDatasetData } from '@fastgpt/service/core/dataset/data/schema';
 import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
-import { TrainingModeEnum } from '@fastgpt/global/core/dataset/constant';
+import { DatasetStatusEnum, TrainingModeEnum } from '@fastgpt/global/core/dataset/constant';
+import { MongoDataset } from '@fastgpt/service/core/dataset/schema';
 
 let success = 0;
 /* pg 中的数据搬到 mongo dataset.datas 中，并做映射 */
@@ -15,32 +16,85 @@ export default async function handler(req: NextApiRequest, res: NextApiResponse)
     await connectToDatabase();
     success = 0;
 
-    await MongoDatasetCollection.updateMany({}, [
+    await MongoDatasetCollection.updateMany({ createTime: { $exists: false } }, [
+      {
+        $set: {
+          createTime: '$updateTime'
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ trainingType: { $exists: false } }, [
       {
         $set: {
-          createTime: '$updateTime',
           trainingType: {
             $cond: {
               if: { $ifNull: ['$a', false] },
               then: TrainingModeEnum.qa,
               else: TrainingModeEnum.chunk
             }
-          },
-          chunkSize: 0,
-          fileId: '$metadata.fileId',
+          }
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ chunkSize: { $exists: false } }, [
+      {
+        $set: {
+          chunkSize: 0
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ fileId: { $exists: false } }, [
+      {
+        $set: {
+          fileId: '$metadata.fileId'
+        }
+      }
+    ]);
+    await MongoDatasetCollection.updateMany({ rawLink: { $exists: false } }, [
+      {
+        $set: {
           rawLink: '$metadata.rawLink'
         }
       }
     ]);
 
     await MongoDatasetData.updateMany(
-      {},
+      { chunkIndex: { $exists: false } },
+      {
+        chunkIndex: 0
+      }
+    );
+    await MongoDatasetData.updateMany(
+      { updateTime: { $exists: false } },
       {
-        chunkIndex: 0,
         updateTime: new Date()
       }
     );
 
+    await MongoDataset.updateMany(
+      { status: { $exists: false } },
+      {
+        $set: {
+          status: DatasetStatusEnum.active
+        }
+      }
+    );
+
+    // dataset tags to intro
+    await MongoDataset.updateMany({ tags: { $exists: true } }, [
+      {
+        $set: {
+          intro: {
+            $reduce: {
+              input: '$tags',
+              initialValue: '',
+              in: { $concat: ['$$value', ' ', '$$this'] }
+            }
+          }
+        }
+      }
+    ]);
+
     jsonRes(res, {
       message: 'success'
     });

projects/app/src/pages/api/admin/timeTasks/checkUnValidDatasetFiles.ts

@@ -0,0 +1,92 @@
+import type { NextApiRequest, NextApiResponse } from 'next';
+import { jsonRes } from '@fastgpt/service/common/response';
+import { connectToDatabase } from '@/service/mongo';
+import { authCert } from '@fastgpt/service/support/permission/auth/common';
+import { delFileById, getGFSCollection } from '@fastgpt/service/common/file/gridfs/controller';
+import { addLog } from '@fastgpt/service/common/mongo/controller';
+import { MongoDatasetCollection } from '@fastgpt/service/core/dataset/collection/schema';
+import { delay } from '@fastgpt/global/common/system/utils';
+
+/* 
+  check dataset.files data. If there is no match in dataset.collections, delete it
+*/
+let deleteFileAmount = 0;
+
+export default async function handler(req: NextApiRequest, res: NextApiResponse) {
+  try {
+    const {
+      startDay = 10,
+      endDay = 3,
+      limit = 30
+    } = req.body as { startDay?: number; endDay?: number; limit?: number };
+    await authCert({ req, authRoot: true });
+    await connectToDatabase();
+
+    // start: now - maxDay, end: now - 3 day
+    const start = new Date(Date.now() - startDay * 24 * 60 * 60 * 1000);
+    const end = new Date(Date.now() - endDay * 24 * 60 * 60 * 1000);
+    deleteFileAmount = 0;
+
+    checkFiles(start, end, limit);
+
+    jsonRes(res, {
+      message: 'success'
+    });
+  } catch (error) {
+    addLog.error(`check valid dataset files error`, error);
+
+    jsonRes(res, {
+      code: 500,
+      error
+    });
+  }
+}
+
+export async function checkFiles(start: Date, end: Date, limit: number) {
+  const collection = getGFSCollection('dataset');
+  const where = {
+    uploadDate: { $gte: start, $lte: end }
+  };
+
+  // 1. get all _id
+  const ids = await collection
+    .find(where, {
+      projection: {
+        _id: 1
+      }
+    })
+    .toArray();
+  console.log('total files', ids.length);
+
+  for (let i = 0; i < limit; i++) {
+    check(i);
+  }
+
+  async function check(index: number): Promise<any> {
+    const id = ids[index];
+    if (!id) {
+      console.log(`检测完成，共删除 ${deleteFileAmount} 个无效文件`);
+
+      return;
+    }
+    try {
+      const { _id } = id;
+
+      // 2. find fileId in dataset.collections
+      const hasCollection = await MongoDatasetCollection.countDocuments({ fileId: _id });
+
+      // 3. if not found, delete file
+      if (hasCollection === 0) {
+        await delFileById({ bucketName: 'dataset', fileId: String(_id) });
+        console.log('delete file', _id);
+        deleteFileAmount++;
+      }
+      index % 100 === 0 && console.log(index);
+      return check(index + limit);
+    } catch (error) {
+      console.log(error);
+      await delay(2000);
+      return check(index);
+    }
+  }
+}