FastGPT/packages/service/core/dataset/schema.ts
Archer 2ccb5b50c6
Some checks are pending
Document deploy / sync-images (push) Waiting to run
Document deploy / generate-timestamp (push) Blocked by required conditions
Document deploy / build-images (map[domain:https://fastgpt.cn suffix:cn]) (push) Blocked by required conditions
Document deploy / build-images (map[domain:https://fastgpt.io suffix:io]) (push) Blocked by required conditions
Document deploy / update-images (map[deployment:fastgpt-docs domain:https://fastgpt.cn kube_config:KUBE_CONFIG_CN suffix:cn]) (push) Blocked by required conditions
Document deploy / update-images (map[deployment:fastgpt-docs domain:https://fastgpt.io kube_config:KUBE_CONFIG_IO suffix:io]) (push) Blocked by required conditions
Build FastGPT images in Personal warehouse / get-vars (push) Waiting to run
Build FastGPT images in Personal warehouse / build-fastgpt-images (map[arch:amd64 runs-on:ubuntu-24.04]) (push) Blocked by required conditions
Build FastGPT images in Personal warehouse / build-fastgpt-images (map[arch:arm64 runs-on:ubuntu-24.04-arm]) (push) Blocked by required conditions
Build FastGPT images in Personal warehouse / release-fastgpt-images (push) Blocked by required conditions
V4.14.4 features (#6036)
* feat: add query optimize and bill (#6021)

* add query optimize and bill

* perf: query extension

* fix: embe model

* remove log

* remove log

* fix: test

---------

Co-authored-by: xxyyh <2289112474@qq>
Co-authored-by: archer <545436317@qq.com>

* feat: notice (#6013)

* feat: record user's language

* feat: notice points/dataset indexes; support count limit; update docker-compose.yml

* fix: ts error

* feat: send auth code i18n

* chore: dataset notice limit

* chore: adjust

* fix: ts

* fix: countLimit race condition; i18n en-prefix locale fallback to en

---------

Co-authored-by: archer <545436317@qq.com>

* perf: comment

* perf: send inform code

* fix: type error (#6029)

* feat: add ip region for chat logs (#6010)

* feat: add ip region for chat logs

* refactor: use Geolite2.mmdb

* fix: export chat logs

* fix: return location directly

* test: add unit test

* perf: log show ip data

* adjust commercial plans (#6008)

* plan frontend

* plan limit

* coupon

* discount coupon

* fix

* type

* fix audit

* type

* plan name

* legacy plan

* track

* feat: add discount coupon

* fix

* fix discount coupon

* openapi

* type

* type

* env

* api type

* fix

* fix: simple agent plugin input & agent dashboard card (#6034)

* refactor: remove gridfs (#6031)

* fix: replace gridfs multer operations with s3 compatible ops

* wip: s3 features

* refactor: remove gridfs

* fix

* perf: mock test

* doc

* doc

* doc

* fix: test

* fix: s3

* fix: mock s3

* remove invalid config

* fix: init query extension

* initv4144 (#6037)

* chore: initv4144

* fix

* version

* fix: new plans (#6039)

* fix: new plans

* qr modal tip

* fix: buffer raw text filename (#6040)

* fix: initv4144 (#6041)

* fix: pay refresh (#6042)

* fix: migration shell

* rename collection

* clear timerlock

* clear timerlock

* perf: faq

* perf: bill schema

* fix: openapi

* doc

* fix: share var render

* feat: delete dataset queue

* plan usage display (#6043)

* plan usage display

* text

* fix

* fix: ts

* perf: remove invalid code

* perf: init shell

* doc

* perf: rename field

* perf: avatar presign

* init

* custom plan text (#6045)

* fix plans

* fix

* fixed

* computed

---------

Co-authored-by: archer <545436317@qq.com>

* init shell

* plan text & price page back button (#6046)

* init

* index

* delete dataset

* delete dataset

* perf: delete dataset

* init

---------

Co-authored-by: YeYuheng <57035043+YYH211@users.noreply.github.com>
Co-authored-by: xxyyh <2289112474@qq>
Co-authored-by: Finley Ge <32237950+FinleyGe@users.noreply.github.com>
Co-authored-by: Roy <whoeverimf5@gmail.com>
Co-authored-by: heheer <heheer@sealos.io>
2025-12-08 01:44:15 +08:00

158 lines
3.2 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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 });
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);