Files
FastGPT/packages/service/core/dataset/controller.ts
Archer 0720bbe4da V4.9.7 feature (#4669)
* update doc

* feat: Add coupon redemption feature for team subscriptions (#4595)

* feat: Add coupon redemption feature for team subscriptions

- Introduced `TeamCouponSub` and `TeamCouponSchema` types
- Added `redeemCoupon` API endpoint
- Updated UI to include a modal for coupon redemption
- Added new icon and translations for "Redeem coupon"

* perf: remove field teamId

* perf: use dynamic import

* refactor: move to page component

* perf: coupon code

* perf: mcp server

* perf: test

* auto layout (#4634)

* fix 4.9.6 (#4631)

* fix debug quote list

* delete next text node match

* fix extract default boolean value

* export latest 100 chat items

* fix quote item ui

* doc

* fix doc

* feat: auto layout

* perf: auto layout

* fix: auto layout null

* add start node

---------

Co-authored-by: heheer <heheer@sealos.io>

* fix: share link (#4644)

* Add workflow run duration;Get audio duration (#4645)

* add duration

* get audio duration

* Custom config path (#4649)

* feat: 通过环境变量DATA_PATH获取配置文件目录 (#4622)

通过环境变量DATA_PATH获取配置文件目录,以应对不同的部署方式的多样化需求

* feat: custom configjson path

* doc

---------

Co-authored-by: John Chen <sss1991@163.com>

* 程序api调用场景下,如果大量调用带有图片或视频,产生的聊天记录会导致后台mongo数据库异常。这个修改给api客户端一个禁止生成聊天记录的选项,避免这个后果。 (#3964)

* update special chatId

* perf: vector db rename

* update operationLog (#4647)

* update operationLog

* combine operationLogMap

* solve operationI18nLogMap bug

* remoce log

* feat: Rerank usage (#4654)

* refresh concat when update (#4655)

* fix: refresh code

* perf: timer lock

* Fix operationLog (#4657)

* perf: http streamable mcp

* add alipay (#4630)

* perf: subplan ui

* perf: pay code

* hiden bank tip

* Fix: pay error (#4665)

* fix quote number (#4666)

* remove log

---------

Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com>
Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: John Chen <sss1991@163.com>
Co-authored-by: gaord <bengao168@msn.com>
Co-authored-by: gggaaallleee <91131304+gggaaallleee@users.noreply.github.com>
2025-04-26 16:17:21 +08:00

120 lines
3.3 KiB
TypeScript

import { DatasetSchemaType } from '@fastgpt/global/core/dataset/type';
import { MongoDatasetCollection } from './collection/schema';
import { MongoDataset } from './schema';
import { delCollectionRelatedSource } from './collection/controller';
import { ClientSession } from '../../common/mongo';
import { MongoDatasetTraining } from './training/schema';
import { MongoDatasetData } from './data/schema';
import { deleteDatasetDataVector } from '../../common/vectorDB/controller';
import { MongoDatasetDataText } from './data/dataTextSchema';
import { DatasetErrEnum } from '@fastgpt/global/common/error/code/dataset';
import { retryFn } from '@fastgpt/global/common/system/utils';
import { removeWebsiteSyncJobScheduler } from './websiteSync';
import { DatasetTypeEnum } from '@fastgpt/global/core/dataset/constants';
/* ============= dataset ========== */
/* find all datasetId by top datasetId */
export async function findDatasetAndAllChildren({
teamId,
datasetId,
fields
}: {
teamId: string;
datasetId: string;
fields?: string;
}): Promise<DatasetSchemaType[]> {
const find = async (id: string) => {
const children = await MongoDataset.find(
{
teamId,
parentId: id
},
fields
).lean();
let datasets = children;
for (const child of children) {
const grandChildrenIds = await find(child._id);
datasets = datasets.concat(grandChildrenIds);
}
return datasets;
};
const [dataset, childDatasets] = await Promise.all([
MongoDataset.findById(datasetId).lean(),
find(datasetId)
]);
if (!dataset) {
return Promise.reject('Dataset not found');
}
return [dataset, ...childDatasets];
}
export async function getCollectionWithDataset(collectionId: string) {
const data = await MongoDatasetCollection.findById(collectionId)
.populate<{ dataset: DatasetSchemaType }>('dataset')
.lean();
if (!data) {
return Promise.reject(DatasetErrEnum.unExistCollection);
}
return data;
}
/* delete all data by datasetIds */
export async function delDatasetRelevantData({
datasets,
session
}: {
datasets: DatasetSchemaType[];
session: ClientSession;
}) {
if (!datasets.length) return;
const teamId = datasets[0].teamId;
if (!teamId) {
return Promise.reject('TeamId is required');
}
const datasetIds = datasets.map((item) => item._id);
// Get _id, teamId, fileId, metadata.relatedImgId for all collections
const collections = await MongoDatasetCollection.find(
{
teamId,
datasetId: { $in: datasetIds }
},
'_id teamId datasetId fileId metadata'
).lean();
await retryFn(async () => {
await Promise.all([
// delete training data
MongoDatasetTraining.deleteMany({
teamId,
datasetId: { $in: datasetIds }
}),
//Delete dataset_data_texts
MongoDatasetDataText.deleteMany({
teamId,
datasetId: { $in: datasetIds }
}),
//delete dataset_datas
MongoDatasetData.deleteMany({ teamId, datasetId: { $in: datasetIds } }),
// Delete Image and file
delCollectionRelatedSource({ collections }),
// Delete vector data
deleteDatasetDataVector({ teamId, datasetIds })
]);
});
// delete collections
await MongoDatasetCollection.deleteMany({
teamId,
datasetId: { $in: datasetIds }
}).session(session);
}