4.6.7 fix (#752)

packages/service/common/file/image/controller.ts

@@ -46,8 +46,17 @@ export async function readMongoImg({ id }: { id: string }) {
   return data?.binary;
 }
 
-export async function delImgByRelatedId(relateIds: string[]) {
+export async function delImgByRelatedId({
+  teamId,
+  relateIds
+}: {
+  teamId: string;
+  relateIds: string[];
+}) {
+  if (relateIds.length === 0) return;
+
   return MongoImage.deleteMany({
+    teamId,
     'metadata.relatedId': { $in: relateIds.map((id) => String(id)) }
   });
 }

packages/service/common/file/image/schema.ts

@@ -34,9 +34,8 @@ const ImageSchema = new Schema({
 try {
   ImageSchema.index({ expiredTime: 1 }, { expireAfterSeconds: 60 });
   ImageSchema.index({ type: 1 });
-  ImageSchema.index({ teamId: 1 });
   ImageSchema.index({ createTime: 1 });
-  ImageSchema.index({ 'metadata.relatedId': 1 });
+  ImageSchema.index({ teamId: 1, 'metadata.relatedId': 1 });
 } catch (error) {
   console.log(error);
 }

packages/service/common/file/multer.ts

@@ -28,12 +28,16 @@ export const getUploadModel = ({ maxSize = 500 }: { maxSize?: number }) => {
         // },
         filename: async (req, file, cb) => {
           const { ext } = path.parse(decodeURIComponent(file.originalname));
-          cb(null, `${getNanoid(32)}${ext}`);
+          cb(null, `${getNanoid()}${ext}`);
         }
       })
     }).single('file');
 
-    async doUpload<T = Record<string, any>>(req: NextApiRequest, res: NextApiResponse) {
+    async doUpload<T = Record<string, any>>(
+      req: NextApiRequest,
+      res: NextApiResponse,
+      originBuckerName?: `${BucketNameEnum}`
+    ) {
       return new Promise<{
         file: FileType;
         metadata: Record<string, any>;
@@ -47,7 +51,7 @@ export const getUploadModel = ({ maxSize = 500 }: { maxSize?: number }) => {
           }
 
           // check bucket name
-          const bucketName = req.body?.bucketName as `${BucketNameEnum}`;
+          const bucketName = (req.body?.bucketName || originBuckerName) as `${BucketNameEnum}`;
           if (bucketName && !bucketNameMap[bucketName]) {
             return reject('BucketName is invalid');
           }

packages/service/common/vectorStore/pg/controller.ts

@@ -39,14 +39,15 @@ export const insertDatasetDataVector = async (
   }
 ): Promise<{ insertId: string }> => {
   const { teamId, datasetId, collectionId, vectors, retry = 3 } = props;
+
   try {
     const { rows } = await PgClient.insert(PgDatasetTableName, {
       values: [
         [
           { key: 'vector', value: `[${vectors[0]}]` },
           { key: 'team_id', value: String(teamId) },
-          { key: 'dataset_id', value: datasetId },
-          { key: 'collection_id', value: collectionId }
+          { key: 'dataset_id', value: String(datasetId) },
+          { key: 'collection_id', value: String(collectionId) }
         ]
       ]
     });
@@ -176,8 +177,8 @@ export const getVectorDataByTime = async (start: Date, end: Date) => {
   `);
 
   return rows.map((item) => ({
-    id: item.id,
-    datasetId: item.dataset_id,
-    teamId: item.team_id
+    id: String(item.id),
+    teamId: item.team_id,
+    datasetId: item.dataset_id
   }));
 };

packages/service/core/chat/chatItemSchema.ts

@@ -89,6 +89,7 @@ try {
      close custom feedback; 
   */
   ChatItemSchema.index({ appId: 1, chatId: 1, dataId: 1 }, { background: true });
+  ChatItemSchema.index({ time: -1 }, { background: true });
   ChatItemSchema.index({ userGoodFeedback: 1 }, { background: true });
   ChatItemSchema.index({ userBadFeedback: 1 }, { background: true });
   ChatItemSchema.index({ customFeedbacks: 1 }, { background: true });

packages/service/core/dataset/collection/controller.ts

@@ -25,7 +25,7 @@ export async function createOneCollection({
   type,
 
   trainingType = TrainingModeEnum.chunk,
-  chunkSize = 0,
+  chunkSize = 512,
   chunkSplitter,
   qaPrompt,
 
@@ -134,7 +134,10 @@ export async function delCollectionAndRelatedSources({
 
   // delete file and imgs
   await Promise.all([
-    delImgByRelatedId(relatedImageIds),
+    delImgByRelatedId({
+      teamId,
+      relateIds: relatedImageIds
+    }),
     delFileByFileIdList({
       bucketName: BucketNameEnum.dataset,
       fileIdList

packages/service/core/dataset/training/controller.ts

@@ -1,5 +1,15 @@
 import { delay } from '@fastgpt/global/common/system/utils';
 import { MongoDatasetTraining } from './schema';
+import type {
+  PushDatasetDataChunkProps,
+  PushDatasetDataProps,
+  PushDatasetDataResponse
+} from '@fastgpt/global/core/dataset/api.d';
+import { getCollectionWithDataset } from '../controller';
+import { TrainingModeEnum } from '@fastgpt/global/core/dataset/constants';
+import { simpleText } from '@fastgpt/global/common/string/tools';
+import { countPromptTokens } from '@fastgpt/global/common/string/tiktoken';
+import type { VectorModelItemType, LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 
 export const lockTrainingDataByTeamId = async (teamId: string, retry = 3): Promise<any> => {
   try {
@@ -19,3 +29,165 @@ export const lockTrainingDataByTeamId = async (teamId: string, retry = 3): Promi
     return Promise.reject(error);
   }
 };
+
+export async function pushDataListToTrainingQueue({
+  teamId,
+  tmbId,
+  collectionId,
+  data,
+  prompt,
+  billId,
+  trainingMode = TrainingModeEnum.chunk,
+
+  vectorModelList = [],
+  qaModelList = []
+}: {
+  teamId: string;
+  tmbId: string;
+  vectorModelList: VectorModelItemType[];
+  qaModelList: LLMModelItemType[];
+} & PushDatasetDataProps): Promise<PushDatasetDataResponse> {
+  const {
+    datasetId: { _id: datasetId, vectorModel, agentModel }
+  } = await getCollectionWithDataset(collectionId);
+
+  const checkModelValid = async ({ collectionId }: { collectionId: string }) => {
+    if (!collectionId) return Promise.reject(`CollectionId is empty`);
+
+    if (trainingMode === TrainingModeEnum.chunk) {
+      const vectorModelData = vectorModelList?.find((item) => item.model === vectorModel);
+      if (!vectorModelData) {
+        return Promise.reject(`Model ${vectorModel} is inValid`);
+      }
+
+      return {
+        maxToken: vectorModelData.maxToken * 1.5,
+        model: vectorModelData.model,
+        weight: vectorModelData.weight
+      };
+    }
+
+    if (trainingMode === TrainingModeEnum.qa) {
+      const qaModelData = qaModelList?.find((item) => item.model === agentModel);
+      if (!qaModelData) {
+        return Promise.reject(`Model ${agentModel} is inValid`);
+      }
+      return {
+        maxToken: qaModelData.maxContext * 0.8,
+        model: qaModelData.model,
+        weight: 0
+      };
+    }
+    return Promise.reject(`Training mode "${trainingMode}" is inValid`);
+  };
+
+  const { model, maxToken, weight } = await checkModelValid({
+    collectionId
+  });
+
+  // format q and a, remove empty char
+  data.forEach((item) => {
+    item.q = simpleText(item.q);
+    item.a = simpleText(item.a);
+
+    item.indexes = item.indexes
+      ?.map((index) => {
+        return {
+          ...index,
+          text: simpleText(index.text)
+        };
+      })
+      .filter(Boolean);
+  });
+
+  // filter repeat or equal content
+  const set = new Set();
+  const filterResult: Record<string, PushDatasetDataChunkProps[]> = {
+    success: [],
+    overToken: [],
+    repeat: [],
+    error: []
+  };
+
+  // filter repeat content
+  data.forEach((item) => {
+    if (!item.q) {
+      filterResult.error.push(item);
+      return;
+    }
+
+    const text = item.q + item.a;
+
+    // count q token
+    const token = countPromptTokens(item.q);
+
+    if (token > maxToken) {
+      filterResult.overToken.push(item);
+      return;
+    }
+
+    if (set.has(text)) {
+      console.log('repeat', item);
+      filterResult.repeat.push(item);
+    } else {
+      filterResult.success.push(item);
+      set.add(text);
+    }
+  });
+
+  // insert data to db
+  const insertData = async (dataList: PushDatasetDataChunkProps[], retry = 3): Promise<number> => {
+    try {
+      const results = await MongoDatasetTraining.insertMany(
+        dataList.map((item, i) => ({
+          teamId,
+          tmbId,
+          datasetId,
+          collectionId,
+          billId,
+          mode: trainingMode,
+          prompt,
+          model,
+          q: item.q,
+          a: item.a,
+          chunkIndex: item.chunkIndex ?? i,
+          weight: weight ?? 0,
+          indexes: item.indexes
+        }))
+      );
+      await delay(500);
+      return results.length;
+    } catch (error) {
+      if (retry > 0) {
+        await delay(500);
+        return insertData(dataList, retry - 1);
+      }
+      return Promise.reject(error);
+    }
+  };
+
+  let insertLen = 0;
+  const chunkSize = 50;
+  const chunkList = filterResult.success.reduce(
+    (acc, cur) => {
+      const lastChunk = acc[acc.length - 1];
+      if (lastChunk.length < chunkSize) {
+        lastChunk.push(cur);
+      } else {
+        acc.push([cur]);
+      }
+      return acc;
+    },
+    [[]] as PushDatasetDataChunkProps[][]
+  );
+  for await (const chunks of chunkList) {
+    insertLen += await insertData(chunks);
+  }
+
+  delete filterResult.success;
+
+  return {
+    insertLen,
+    ...filterResult
+  };
+}

packages/service/support/wallet/bill/schema.ts

@@ -52,7 +52,7 @@ const BillSchema = new Schema({
 });
 
 try {
-  BillSchema.index({ teamId: 1, tmbId: 1, time: -1 });
+  BillSchema.index({ teamId: 1, time: -1 });
   BillSchema.index({ time: 1 }, { expireAfterSeconds: 180 * 24 * 60 * 60 });
 } catch (error) {
   console.log(error);