mirror of
https://github.com/labring/FastGPT.git
synced 2026-05-07 01:02:55 +08:00
36d1ff3679
* perf: faq * index * delete dataset * delete dataset * perf: delete dataset * init * fix: faq * doc * fix: share link auth (#6063) * standard plan add custom domain config (#6061) * standard plan add custom domain config * bill detail modal * perf: vector count api * feat: custom domain & wecom bot SaaS integration (#6047) * feat: custom Domain type define * feat: custom domain * feat: wecom custom domain * chore: i18n * chore: i18n; team auth * feat: wecom multi-model message support * chore: wecom edit modal * chore(doc): custom domain && wecom bot * fix: type * fix: type * fix: file detect * feat: fe * fix: img name * fix: test * compress img * rename * editor initial status * fix: chat url * perf: s3 upload by buffer * img * refresh * fix: custom domain selector (#6069) * empty tip * perf: s3 init * sort provider * fix: extend * perf: extract filename --------- Co-authored-by: Roy <whoeverimf5@gmail.com> Co-authored-by: heheer <heheer@sealos.io> Co-authored-by: Finley Ge <32237950+FinleyGe@users.noreply.github.com>
158 lines
3.2 KiB
TypeScript
158 lines
3.2 KiB
TypeScript
import { getMongoModel, Schema } from '../../common/mongo';
|
|
import {
|
|
ChunkSettingModeEnum,
|
|
ChunkTriggerConfigTypeEnum,
|
|
DataChunkSplitModeEnum,
|
|
DatasetCollectionDataProcessModeEnum,
|
|
DatasetTypeEnum,
|
|
DatasetTypeMap,
|
|
ParagraphChunkAIModeEnum
|
|
} from '@fastgpt/global/core/dataset/constants';
|
|
import {
|
|
TeamCollectionName,
|
|
TeamMemberCollectionName
|
|
} from '@fastgpt/global/support/user/team/constant';
|
|
import type { DatasetSchemaType } from '@fastgpt/global/core/dataset/type.d';
|
|
|
|
export const DatasetCollectionName = 'datasets';
|
|
|
|
export const ChunkSettings = {
|
|
trainingType: {
|
|
type: String,
|
|
enum: Object.values(DatasetCollectionDataProcessModeEnum)
|
|
},
|
|
|
|
chunkTriggerType: {
|
|
type: String,
|
|
enum: Object.values(ChunkTriggerConfigTypeEnum)
|
|
},
|
|
chunkTriggerMinSize: Number,
|
|
|
|
dataEnhanceCollectionName: Boolean,
|
|
|
|
imageIndex: Boolean,
|
|
autoIndexes: Boolean,
|
|
indexPrefixTitle: Boolean,
|
|
|
|
chunkSettingMode: {
|
|
type: String,
|
|
enum: Object.values(ChunkSettingModeEnum)
|
|
},
|
|
chunkSplitMode: {
|
|
type: String,
|
|
enum: Object.values(DataChunkSplitModeEnum)
|
|
},
|
|
paragraphChunkAIMode: {
|
|
type: String,
|
|
enum: Object.values(ParagraphChunkAIModeEnum)
|
|
},
|
|
paragraphChunkDeep: Number,
|
|
paragraphChunkMinSize: Number,
|
|
chunkSize: Number,
|
|
chunkSplitter: String,
|
|
|
|
indexSize: Number,
|
|
qaPrompt: String
|
|
};
|
|
|
|
const DatasetSchema = new Schema({
|
|
parentId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: DatasetCollectionName,
|
|
default: null
|
|
},
|
|
userId: {
|
|
//abandon
|
|
type: Schema.Types.ObjectId,
|
|
ref: 'user'
|
|
},
|
|
teamId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: TeamCollectionName,
|
|
required: true
|
|
},
|
|
tmbId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: TeamMemberCollectionName,
|
|
required: true
|
|
},
|
|
type: {
|
|
type: String,
|
|
enum: Object.keys(DatasetTypeMap),
|
|
required: true,
|
|
default: DatasetTypeEnum.dataset
|
|
},
|
|
avatar: {
|
|
type: String,
|
|
default: '/icon/logo.svg'
|
|
},
|
|
name: {
|
|
type: String,
|
|
required: true
|
|
},
|
|
updateTime: {
|
|
type: Date,
|
|
default: () => new Date()
|
|
},
|
|
vectorModel: {
|
|
type: String,
|
|
required: true,
|
|
default: 'text-embedding-3-small'
|
|
},
|
|
agentModel: {
|
|
type: String,
|
|
required: true,
|
|
default: 'gpt-4o-mini'
|
|
},
|
|
vlmModel: String,
|
|
intro: {
|
|
type: String,
|
|
default: ''
|
|
},
|
|
websiteConfig: {
|
|
type: {
|
|
url: {
|
|
type: String,
|
|
required: true
|
|
},
|
|
selector: {
|
|
type: String,
|
|
default: 'body'
|
|
}
|
|
}
|
|
},
|
|
chunkSettings: {
|
|
type: ChunkSettings
|
|
},
|
|
inheritPermission: {
|
|
type: Boolean,
|
|
default: true
|
|
},
|
|
|
|
apiDatasetServer: Object,
|
|
|
|
// 软删除标记字段
|
|
deleteTime: {
|
|
type: Date,
|
|
default: null // null表示未删除,有值表示删除时间
|
|
},
|
|
|
|
// abandoned
|
|
autoSync: Boolean,
|
|
externalReadUrl: String,
|
|
defaultPermission: Number,
|
|
apiServer: Object,
|
|
feishuServer: Object,
|
|
yuqueServer: Object
|
|
});
|
|
|
|
try {
|
|
DatasetSchema.index({ teamId: 1 });
|
|
DatasetSchema.index({ type: 1 }); // Admin count
|
|
DatasetSchema.index({ deleteTime: 1 }); // 添加软删除字段索引
|
|
} catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
export const MongoDataset = getMongoModel<DatasetSchemaType>(DatasetCollectionName, DatasetSchema);
|