mirror of
https://github.com/labring/FastGPT.git
synced 2025-10-14 15:11:13 +00:00
V4.8.17 feature (#3485)
* feat: add third party account config (#3443) * temp * editor workflow variable style * add team to dispatch * i18n * delete console * change openai account position * fix * fix * fix * fix * fix * 4.8.17 test (#3461) * perf: external provider config * perf: ui * feat: add template config (#3434) * change template position * template config * delete console * delete * fix * fix * perf: Mongo visutal field (#3464) * remve invalid code * perf: team member visutal code * perf: virtual search; perf: search test data * fix: ts * fix: image response headers * perf: template code * perf: auth layout;perf: auto save (#3472) * perf: auth layout * perf: auto save * perf: auto save * fix: template guide display & http input support external variables (#3475) * fix: template guide display * http editor support external workflow variables * perf: auto save;fix: ifelse checker line break; (#3478) * perf: auto save * perf: auto save * fix: ifelse checker line break * perf: doc * perf: doc * fix: update var type error * 4.8.17 test (#3479) * perf: auto save * perf: auto save * perf: template code * 4.8.17 test (#3480) * perf: auto save * perf: auto save * perf: model price model * feat: add react memo * perf: model provider filter * fix: ts (#3481) * perf: auto save * perf: auto save * fix: ts * simple app tool select (#3473) * workflow plugin userguide & simple tool ui * simple tool filter * reuse component * change component to hook * fix * perf: too selector modal (#3484) * perf: auto save * perf: auto save * perf: markdown render * perf: too selector * fix: app version require tmbId * perf: templates refresh * perf: templates refresh * hide auto save error tip * perf: toolkit guide --------- Co-authored-by: heheer <heheer@sealos.io>
This commit is contained in:
@@ -4,11 +4,7 @@ import {
|
||||
} from '@fastgpt/global/core/dataset/constants';
|
||||
import type { CreateDatasetCollectionParams } from '@fastgpt/global/core/dataset/api.d';
|
||||
import { MongoDatasetCollection } from './schema';
|
||||
import {
|
||||
CollectionWithDatasetType,
|
||||
DatasetCollectionSchemaType,
|
||||
DatasetSchemaType
|
||||
} from '@fastgpt/global/core/dataset/type';
|
||||
import { DatasetCollectionSchemaType, DatasetSchemaType } from '@fastgpt/global/core/dataset/type';
|
||||
import { MongoDatasetTraining } from '../training/schema';
|
||||
import { MongoDatasetData } from '../data/schema';
|
||||
import { delImgByRelatedId } from '../../../common/file/image/controller';
|
||||
@@ -230,7 +226,7 @@ export const delCollectionRelatedSource = async ({
|
||||
collections,
|
||||
session
|
||||
}: {
|
||||
collections: (CollectionWithDatasetType | DatasetCollectionSchemaType)[];
|
||||
collections: DatasetCollectionSchemaType[];
|
||||
session: ClientSession;
|
||||
}) => {
|
||||
if (collections.length === 0) return;
|
||||
@@ -264,7 +260,7 @@ export async function delCollection({
|
||||
session,
|
||||
delRelatedSource
|
||||
}: {
|
||||
collections: (CollectionWithDatasetType | DatasetCollectionSchemaType)[];
|
||||
collections: DatasetCollectionSchemaType[];
|
||||
session: ClientSession;
|
||||
delRelatedSource: boolean;
|
||||
}) {
|
||||
@@ -274,16 +270,7 @@ export async function delCollection({
|
||||
|
||||
if (!teamId) return Promise.reject('teamId is not exist');
|
||||
|
||||
const datasetIds = Array.from(
|
||||
new Set(
|
||||
collections.map((item) => {
|
||||
if (typeof item.datasetId === 'string') {
|
||||
return String(item.datasetId);
|
||||
}
|
||||
return String(item.datasetId._id);
|
||||
})
|
||||
)
|
||||
);
|
||||
const datasetIds = Array.from(new Set(collections.map((item) => String(item.datasetId))));
|
||||
const collectionIds = collections.map((item) => String(item._id));
|
||||
|
||||
// delete training data
|
||||
@@ -324,7 +311,7 @@ export async function delOnlyCollection({
|
||||
collections,
|
||||
session
|
||||
}: {
|
||||
collections: (CollectionWithDatasetType | DatasetCollectionSchemaType)[];
|
||||
collections: DatasetCollectionSchemaType[];
|
||||
session: ClientSession;
|
||||
}) {
|
||||
if (collections.length === 0) return;
|
||||
@@ -333,16 +320,7 @@ export async function delOnlyCollection({
|
||||
|
||||
if (!teamId) return Promise.reject('teamId is not exist');
|
||||
|
||||
const datasetIds = Array.from(
|
||||
new Set(
|
||||
collections.map((item) => {
|
||||
if (typeof item.datasetId === 'string') {
|
||||
return String(item.datasetId);
|
||||
}
|
||||
return String(item.datasetId._id);
|
||||
})
|
||||
)
|
||||
);
|
||||
const datasetIds = Array.from(new Set(collections.map((item) => String(item.datasetId))));
|
||||
const collectionIds = collections.map((item) => String(item._id));
|
||||
|
||||
// delete training data
|
||||
|
@@ -100,6 +100,13 @@ const DatasetCollectionSchema = new Schema({
|
||||
}
|
||||
});
|
||||
|
||||
DatasetCollectionSchema.virtual('dataset', {
|
||||
ref: DatasetCollectionName,
|
||||
localField: 'datasetId',
|
||||
foreignField: '_id',
|
||||
justOne: true
|
||||
});
|
||||
|
||||
try {
|
||||
// auth file
|
||||
DatasetCollectionSchema.index({ teamId: 1, fileId: 1 });
|
||||
|
@@ -130,7 +130,7 @@ export const collectionTagsToTagLabel = async ({
|
||||
};
|
||||
|
||||
export const syncCollection = async (collection: CollectionWithDatasetType) => {
|
||||
const dataset = collection.datasetId;
|
||||
const dataset = collection.dataset;
|
||||
|
||||
if (
|
||||
collection.type !== DatasetCollectionTypeEnum.link &&
|
||||
@@ -183,7 +183,7 @@ export const syncCollection = async (collection: CollectionWithDatasetType) => {
|
||||
teamId: collection.teamId,
|
||||
tmbId: collection.tmbId,
|
||||
name: collection.name,
|
||||
datasetId: collection.datasetId._id,
|
||||
datasetId: collection.datasetId,
|
||||
parentId: collection.parentId,
|
||||
type: collection.type,
|
||||
|
||||
|
@@ -1,4 +1,4 @@
|
||||
import { CollectionWithDatasetType, DatasetSchemaType } from '@fastgpt/global/core/dataset/type';
|
||||
import { DatasetSchemaType } from '@fastgpt/global/core/dataset/type';
|
||||
import { MongoDatasetCollection } from './collection/schema';
|
||||
import { MongoDataset } from './schema';
|
||||
import { delCollectionRelatedSource } from './collection/controller';
|
||||
@@ -49,9 +49,9 @@ export async function findDatasetAndAllChildren({
|
||||
}
|
||||
|
||||
export async function getCollectionWithDataset(collectionId: string) {
|
||||
const data = (await MongoDatasetCollection.findById(collectionId)
|
||||
.populate('datasetId')
|
||||
.lean()) as CollectionWithDatasetType;
|
||||
const data = await MongoDatasetCollection.findById(collectionId)
|
||||
.populate<{ dataset: DatasetSchemaType }>('dataset')
|
||||
.lean();
|
||||
if (!data) {
|
||||
return Promise.reject('Collection is not exist');
|
||||
}
|
||||
|
@@ -77,21 +77,32 @@ const DatasetDataSchema = new Schema({
|
||||
rebuilding: Boolean
|
||||
});
|
||||
|
||||
// list collection and count data; list data; delete collection(relate data)
|
||||
DatasetDataSchema.index({
|
||||
teamId: 1,
|
||||
datasetId: 1,
|
||||
collectionId: 1,
|
||||
chunkIndex: 1,
|
||||
updateTime: -1
|
||||
DatasetDataSchema.virtual('collection', {
|
||||
ref: DatasetColCollectionName,
|
||||
localField: 'collectionId',
|
||||
foreignField: '_id',
|
||||
justOne: true
|
||||
});
|
||||
// full text index
|
||||
DatasetDataSchema.index({ teamId: 1, datasetId: 1, fullTextToken: 'text' });
|
||||
// Recall vectors after data matching
|
||||
DatasetDataSchema.index({ teamId: 1, datasetId: 1, collectionId: 1, 'indexes.dataId': 1 });
|
||||
DatasetDataSchema.index({ updateTime: 1 });
|
||||
// rebuild data
|
||||
DatasetDataSchema.index({ rebuilding: 1, teamId: 1, datasetId: 1 });
|
||||
|
||||
try {
|
||||
// list collection and count data; list data; delete collection(relate data)
|
||||
DatasetDataSchema.index({
|
||||
teamId: 1,
|
||||
datasetId: 1,
|
||||
collectionId: 1,
|
||||
chunkIndex: 1,
|
||||
updateTime: -1
|
||||
});
|
||||
// full text index
|
||||
DatasetDataSchema.index({ teamId: 1, datasetId: 1, fullTextToken: 'text' });
|
||||
// Recall vectors after data matching
|
||||
DatasetDataSchema.index({ teamId: 1, datasetId: 1, collectionId: 1, 'indexes.dataId': 1 });
|
||||
DatasetDataSchema.index({ updateTime: 1 });
|
||||
// rebuild data
|
||||
DatasetDataSchema.index({ rebuilding: 1, teamId: 1, datasetId: 1 });
|
||||
} catch (error) {
|
||||
console.log(error);
|
||||
}
|
||||
|
||||
export const MongoDatasetData = getMongoModel<DatasetDataSchemaType>(
|
||||
DatasetDataCollectionName,
|
||||
|
@@ -8,8 +8,8 @@ import { getVectorsByText } from '../../ai/embedding';
|
||||
import { getVectorModel } from '../../ai/model';
|
||||
import { MongoDatasetData } from '../data/schema';
|
||||
import {
|
||||
DatasetCollectionSchemaType,
|
||||
DatasetDataSchemaType,
|
||||
DatasetDataWithCollectionType,
|
||||
SearchDataResponseItemType
|
||||
} from '@fastgpt/global/core/dataset/type';
|
||||
import { MongoDatasetCollection } from '../collection/schema';
|
||||
@@ -267,7 +267,7 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
|
||||
});
|
||||
|
||||
// get q and a
|
||||
const dataList = (await MongoDatasetData.find(
|
||||
const dataList = await MongoDatasetData.find(
|
||||
{
|
||||
teamId,
|
||||
datasetId: { $in: datasetIds },
|
||||
@@ -276,8 +276,11 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
|
||||
},
|
||||
'datasetId collectionId updateTime q a chunkIndex indexes'
|
||||
)
|
||||
.populate('collectionId', 'name fileId rawLink externalFileId externalFileUrl')
|
||||
.lean()) as DatasetDataWithCollectionType[];
|
||||
.populate<{ collection: DatasetCollectionSchemaType }>(
|
||||
'collection',
|
||||
'name fileId rawLink externalFileId externalFileUrl'
|
||||
)
|
||||
.lean();
|
||||
|
||||
// add score to data(It's already sorted. The first one is the one with the most points)
|
||||
const concatResults = dataList.map((data) => {
|
||||
@@ -307,8 +310,8 @@ export async function searchDatasetData(props: SearchDatasetDataProps) {
|
||||
a: data.a,
|
||||
chunkIndex: data.chunkIndex,
|
||||
datasetId: String(data.datasetId),
|
||||
collectionId: String(data.collectionId?._id),
|
||||
...getCollectionSourceData(data.collectionId),
|
||||
collectionId: String(data.collectionId),
|
||||
...getCollectionSourceData(data.collection),
|
||||
score: [{ type: SearchScoreTypeEnum.embedding, value: data.score, index }]
|
||||
};
|
||||
|
||||
|
@@ -34,7 +34,7 @@ export const pushDataListToTrainingQueueByCollectionId = async ({
|
||||
session?: ClientSession;
|
||||
} & PushDatasetDataProps) => {
|
||||
const {
|
||||
datasetId: { _id: datasetId, agentModel, vectorModel }
|
||||
dataset: { _id: datasetId, agentModel, vectorModel }
|
||||
} = await getCollectionWithDataset(collectionId);
|
||||
return pushDataListToTrainingQueue({
|
||||
...props,
|
||||
|
Reference in New Issue
Block a user