Update docs and response tag in share page (#694)

* perf: chunk index show

* share response

* perf: vector query

* web printFinger

* remove log

* fix: bucket name

* perf: training schema

* perf: sort index

packages/service/common/file/upload/multer.ts

@@ -2,7 +2,7 @@ import type { NextApiRequest, NextApiResponse } from 'next';
 import { customAlphabet } from 'nanoid';
 import multer from 'multer';
 import path from 'path';
-import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
+import { BucketNameEnum, bucketNameMap } from '@fastgpt/global/common/file/constants';
 import fs from 'fs';
 
 const nanoid = customAlphabet('1234567890abcdef', 12);
@@ -45,6 +45,12 @@ export function getUploadModel({ maxSize = 500 }: { maxSize?: number }) {
             return reject(error);
           }
 
+          // check bucket name
+          const bucketName = req.body?.bucketName as `${BucketNameEnum}`;
+          if (bucketName && !bucketNameMap[bucketName]) {
+            return reject('BucketName is invalid');
+          }
+
           resolve({
             ...req.body,
             files:

packages/service/common/vectorStore/controller.ts

@@ -48,7 +48,7 @@ export const updateDatasetDataVector = async ({
   // get vector
   const { vectors, tokens } = await getVectorsByText({
     model,
-    input: [query]
+    input: query
   });
 
   await getVectorObj().update({

packages/service/core/ai/embedding/index.ts

@@ -2,7 +2,7 @@ import { getAIApi } from '../config';
 
 export type GetVectorProps = {
   model: string;
-  input: string | string[];
+  input: string;
 };
 
 // text to vector
@@ -10,24 +10,13 @@ export async function getVectorsByText({
   model = 'text-embedding-ada-002',
   input
 }: GetVectorProps) {
-  if (typeof input === 'string' && !input) {
+  if (!input) {
     return Promise.reject({
       code: 500,
       message: 'input is empty'
     });
-  } else if (Array.isArray(input)) {
-    for (let i = 0; i < input.length; i++) {
-      if (!input[i]) {
-        return Promise.reject({
-          code: 500,
-          message: 'input array is empty'
-        });
-      }
-    }
-  }
-  if (typeof input === 'string') {
-    input = [input];
   }
+
   try {
     // 获取 chatAPI
     const ai = getAIApi();
@@ -36,7 +25,7 @@ export async function getVectorsByText({
     const result = await ai.embeddings
       .create({
         model,
-        input
+        input: [input]
       })
       .then(async (res) => {
         if (!res.data) {
@@ -47,6 +36,7 @@ export async function getVectorsByText({
           // @ts-ignore
           return Promise.reject(res.data?.err?.message || 'Embedding API Error');
         }
+
         return {
           tokens: res.usage.total_tokens || 0,
           vectors: await Promise.all(res.data.map((item) => unityDimensional(item.embedding)))

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

@@ -102,6 +102,7 @@ const TrainingDataSchema = new Schema({
 });
 
 try {
+  TrainingDataSchema.index({ weight: -1 });
   TrainingDataSchema.index({ lockTime: 1 });
   TrainingDataSchema.index({ datasetId: 1 });
   TrainingDataSchema.index({ collectionId: 1 });