mirror of
https://github.com/labring/FastGPT.git
synced 2025-10-15 15:41:05 +00:00

* add dynamic inputRender (#5127) * dynamic input component * fix * fix * fix * perf: dynamic render input * update doc * perf: error catch * num input ui * fix form render (#5177) * perf: i18n check * add log * doc * Sync dataset (#5181) * perf: api dataset create (#5047) * Sync dataset (#5120) * add * wait * restructure dataset sync, update types and APIs, add sync hints, and remove legacy logic * feat: add function to retrieve real file ID from third-party doc library and rename team permission check function for clarity * fix come console * refactor: rename team dataset limit check functions for clarity, update API dataset sync limit usage, and rename root directory to "ROOT_FOLDER" * frat: update sync dataset login * fix delete.ts * feat: update pnpm-lock.yaml to include bullmq, fix comments in api.d.ts and type.d.ts, rename API file ID field, optimize dataset sync logic, and add website sync feature with related APIs * feat: update CollectionCard to support site dataset sync, add API root ID constant and init sync API * feat: add RootCollectionId constant to replace hardcoded root ID --------- Co-authored-by: dreamer6680 <146868355@qq.com> * perf: code * feat: update success message for dataset sync, revise related i18n texts, and optimize file selection logic (#5166) Co-authored-by: dreamer6680 <146868355@qq.com> * perf: select file * Sync dataset (#5180) * feat: update success message for dataset sync, revise related i18n texts, and optimize file selection logic * fix: make listfile function return rawid string --------- Co-authored-by: dreamer6680 <146868355@qq.com> * init sh * fix: ts --------- Co-authored-by: dreamer6680 <1468683855@qq.com> Co-authored-by: dreamer6680 <146868355@qq.com> * update doc * i18n --------- Co-authored-by: heheer <heheer@sealos.io> Co-authored-by: dreamer6680 <1468683855@qq.com> Co-authored-by: dreamer6680 <146868355@qq.com>
138 lines
2.9 KiB
TypeScript
138 lines
2.9 KiB
TypeScript
import { connectionMongo, getMongoModel } from '../../../common/mongo';
|
|
const { Schema } = connectionMongo;
|
|
import { type DatasetCollectionSchemaType } from '@fastgpt/global/core/dataset/type.d';
|
|
import { DatasetCollectionTypeMap } from '@fastgpt/global/core/dataset/constants';
|
|
import { ChunkSettings, DatasetCollectionName } from '../schema';
|
|
import {
|
|
TeamCollectionName,
|
|
TeamMemberCollectionName
|
|
} from '@fastgpt/global/support/user/team/constant';
|
|
|
|
export const DatasetColCollectionName = 'dataset_collections';
|
|
|
|
const DatasetCollectionSchema = new Schema({
|
|
parentId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: DatasetColCollectionName,
|
|
default: null
|
|
},
|
|
teamId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: TeamCollectionName,
|
|
required: true
|
|
},
|
|
tmbId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: TeamMemberCollectionName,
|
|
required: true
|
|
},
|
|
datasetId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: DatasetCollectionName,
|
|
required: true
|
|
},
|
|
|
|
// Basic info
|
|
type: {
|
|
type: String,
|
|
enum: Object.keys(DatasetCollectionTypeMap),
|
|
required: true
|
|
},
|
|
name: {
|
|
type: String,
|
|
required: true
|
|
},
|
|
tags: {
|
|
type: [String],
|
|
default: []
|
|
},
|
|
|
|
createTime: {
|
|
type: Date,
|
|
default: () => new Date()
|
|
},
|
|
updateTime: {
|
|
type: Date,
|
|
default: () => new Date()
|
|
},
|
|
|
|
// Metadata
|
|
// local file collection
|
|
fileId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: 'dataset.files'
|
|
},
|
|
// web link collection
|
|
rawLink: String,
|
|
// Api collection
|
|
apiFileId: String,
|
|
// external collection(Abandoned)
|
|
externalFileId: String,
|
|
externalFileUrl: String, // external import url
|
|
|
|
rawTextLength: Number,
|
|
hashRawText: String,
|
|
metadata: {
|
|
type: Object,
|
|
default: {}
|
|
},
|
|
|
|
forbid: Boolean,
|
|
|
|
// Parse settings
|
|
customPdfParse: Boolean,
|
|
apiFileParentId: String,
|
|
|
|
// Chunk settings
|
|
...ChunkSettings
|
|
});
|
|
|
|
DatasetCollectionSchema.virtual('dataset', {
|
|
ref: DatasetCollectionName,
|
|
localField: 'datasetId',
|
|
foreignField: '_id',
|
|
justOne: true
|
|
});
|
|
|
|
try {
|
|
// auth file
|
|
DatasetCollectionSchema.index({ teamId: 1, fileId: 1 });
|
|
|
|
// list collection; deep find collections
|
|
DatasetCollectionSchema.index({
|
|
teamId: 1,
|
|
datasetId: 1,
|
|
parentId: 1,
|
|
updateTime: -1
|
|
});
|
|
|
|
// Tag filter
|
|
DatasetCollectionSchema.index({ teamId: 1, datasetId: 1, tags: 1 });
|
|
// create time filter
|
|
DatasetCollectionSchema.index({ teamId: 1, datasetId: 1, createTime: 1 });
|
|
|
|
// Get collection by external file id
|
|
DatasetCollectionSchema.index(
|
|
{ datasetId: 1, externalFileId: 1 },
|
|
{
|
|
unique: true,
|
|
partialFilterExpression: {
|
|
externalFileId: { $exists: true }
|
|
}
|
|
}
|
|
);
|
|
|
|
// Clear invalid image
|
|
DatasetCollectionSchema.index({
|
|
teamId: 1,
|
|
'metadata.relatedImgId': 1
|
|
});
|
|
} catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
export const MongoDatasetCollection = getMongoModel<DatasetCollectionSchemaType>(
|
|
DatasetColCollectionName,
|
|
DatasetCollectionSchema
|
|
);
|