doc and config rerank (#475)

2025-07-23 13:03:50 +00:00 · 2023-11-16 10:46:47 +08:00
parent cd3acb44ab
commit 16103029f5
18 changed files with 158 additions and 55 deletions
--- a/projects/app/public/locales/en/common.json
+++ b/projects/app/public/locales/en/common.json
@@ -317,6 +317,9 @@
    },
    "deleteDatasetTips": "Are you sure to delete the knowledge base? Data cannot be recovered after deletion, please confirm!",
    "deleteFolderTips": "Are you sure to delete this folder and all the knowledge bases it contains? Data cannot be recovered after deletion, please confirm!",
+    "recall": {
+      "rerank": "Rerank"
+    },
    "test": {
      "noResult": "Search results are empty"
    }
--- a/projects/app/public/locales/zh/common.json
+++ b/projects/app/public/locales/zh/common.json
@@ -317,6 +317,9 @@
    },
    "deleteDatasetTips": "确认删除该知识库？删除后数据无法恢复，请确认！",
    "deleteFolderTips": "确认删除该文件夹及其包含的所有知识库？删除后数据无法恢复，请确认！",
+    "recall": {
+      "rerank": "结果重排"
+    },
    "test": {
      "noResult": "搜索结果为空"
    }
--- a/projects/app/src/components/core/module/DatasetSelectModal.tsx
+++ b/projects/app/src/components/core/module/DatasetSelectModal.tsx
@@ -9,7 +9,8 @@ import {
  useTheme,
  Textarea,
  Grid,
-  Divider
+  Divider,
+  Switch
 } from '@chakra-ui/react';
 import Avatar from '@/components/Avatar';
 import { useForm } from 'react-hook-form';
@@ -30,6 +31,7 @@ export type KbParamsType = {
  searchSimilarity: number;
  searchLimit: number;
  searchEmptyText: string;
+  rerank: boolean;
 };

 export const DatasetSelectModal = ({
@@ -225,10 +227,11 @@ export const DatasetSelectModal = ({
  );
 };

-export const KbParamsModal = ({
+export const DatasetParamsModal = ({
  searchEmptyText,
  searchLimit,
  searchSimilarity,
+  rerank,
  onClose,
  onChange
 }: KbParamsType & { onClose: () => void; onChange: (e: KbParamsType) => void }) => {
@@ -237,7 +240,8 @@ export const KbParamsModal = ({
    defaultValues: {
      searchEmptyText,
      searchLimit,
-      searchSimilarity
+      searchSimilarity,
+      rerank
    }
  });

@@ -245,6 +249,24 @@ export const KbParamsModal = ({
    <MyModal isOpen={true} onClose={onClose} title={'搜索参数调整'} minW={['90vw', '600px']}>
      <Flex flexDirection={'column'}>
        <ModalBody>
+          {feConfigs?.isPlus && (
+            <Box display={['block', 'flex']} py={5} pt={[0, 5]}>
+              <Box flex={'0 0 100px'} mb={[8, 0]}>
+                结果重排
+                <MyTooltip label={'将召回的结果进行进一步重排，可增加召回率'} forceShow>
+                  <QuestionOutlineIcon ml={1} />
+                </MyTooltip>
+              </Box>
+              <Switch
+                size={'lg'}
+                isChecked={getValues('rerank')}
+                onChange={(e) => {
+                  setValue('rerank', e.target.checked);
+                  setRefresh(!refresh);
+                }}
+              />
+            </Box>
+          )}
          <Box display={['block', 'flex']} py={5} pt={[0, 5]}>
            <Box flex={'0 0 100px'} mb={[8, 0]}>
              相似度
--- a/projects/app/src/components/core/module/Flow/components/render/RenderInput.tsx
+++ b/projects/app/src/components/core/module/Flow/components/render/RenderInput.tsx
@@ -14,7 +14,8 @@ import {
  useDisclosure,
  Button,
  useTheme,
-  Grid
+  Grid,
+  Switch
 } from '@chakra-ui/react';
 import { FlowNodeInputTypeEnum } from '@fastgpt/global/core/module/node/constant';
 import { QuestionOutlineIcon } from '@chakra-ui/icons';
@@ -35,6 +36,7 @@ import type { SelectedDatasetType } from '@fastgpt/global/core/module/api.d';
 import { useQuery } from '@tanstack/react-query';
 import type { LLMModelItemType } from '@fastgpt/global/core/ai/model.d';
 import type { EditFieldModeType, EditFieldType } from '../modules/FieldEditModal';
+import { feConfigs } from '@/web/common/system/staticData';

 const FieldEditModal = dynamic(() => import('../modules/FieldEditModal'));
 const SelectAppModal = dynamic(() => import('../../SelectAppModal'));
@@ -163,7 +165,10 @@ const RenderInput = ({
  editFiledType?: EditFieldModeType;
 }) => {
  const sortInputs = useMemo(
-    () => flowInputList.sort((a, b) => (a.key === FlowNodeInputTypeEnum.switch ? -1 : 1)),
+    () =>
+      flowInputList
+        .filter((item) => !item.plusField || feConfigs.isPlus)
+        .sort((a, b) => (a.key === FlowNodeInputTypeEnum.switch ? -1 : 1)),
    [flowInputList]
  );
  return (
@@ -187,6 +192,9 @@ const RenderInput = ({
                {item.type === FlowNodeInputTypeEnum.input && (
                  <TextInputRender item={item} moduleId={moduleId} />
                )}
+                {item.type === FlowNodeInputTypeEnum.switch && (
+                  <SwitchRender item={item} moduleId={moduleId} />
+                )}
                {item.type === FlowNodeInputTypeEnum.textarea && (
                  <TextareaRender item={item} moduleId={moduleId} />
                )}
@@ -277,6 +285,26 @@ var TextInputRender = React.memo(function TextInputRender({ item, moduleId }: Re
  );
 });

+var SwitchRender = React.memo(function SwitchRender({ item, moduleId }: RenderProps) {
+  return (
+    <Switch
+      size={'lg'}
+      isChecked={item.value}
+      onChange={(e) => {
+        onChangeNode({
+          moduleId,
+          type: 'updateInput',
+          key: item.key,
+          value: {
+            ...item,
+            value: e.target.checked
+          }
+        });
+      }}
+    />
+  );
+});
+
 var TextareaRender = React.memo(function TextareaRender({ item, moduleId }: RenderProps) {
  return (
    <Textarea
--- a/projects/app/src/constants/flow/ModuleTemplate.ts
+++ b/projects/app/src/constants/flow/ModuleTemplate.ts
@@ -292,6 +292,14 @@ export const DatasetSearchModule: FlowModuleTemplateType = {
        { label: '20', value: 20 }
      ]
    },
+    {
+      key: 'rerank',
+      type: FlowNodeInputTypeEnum.switch,
+      label: '结果重排',
+      description: '将召回的结果进行进一步重排，可增加召回率',
+      plusField: true,
+      value: false
+    },
    Input_Template_UserChatInput
  ],
  outputs: [
--- a/projects/app/src/global/core/api/datasetReq.d.ts
+++ b/projects/app/src/global/core/api/datasetReq.d.ts
@@ -22,6 +22,7 @@ export type SearchTestProps = {
  datasetId: string;
  text: string;
  limit?: number;
+  rerank?: boolean;
 };

 /* ======= collections =========== */
--- a/projects/app/src/pages/api/core/dataset/searchTest.ts
+++ b/projects/app/src/pages/api/core/dataset/searchTest.ts
@@ -16,7 +16,7 @@ import { BillSourceEnum } from '@fastgpt/global/support/wallet/bill/constants';
 export default withNextCors(async function handler(req: NextApiRequest, res: NextApiResponse<any>) {
  try {
    await connectToDatabase();
-    const { datasetId, text, limit = 20 } = req.body as SearchTestProps;
+    const { datasetId, text, limit = 20, rerank } = req.body as SearchTestProps;

    if (!datasetId || !text) {
      throw new Error('缺少参数');
@@ -38,7 +38,8 @@ export default withNextCors(async function handler(req: NextApiRequest, res: Nex
      text,
      model: dataset.vectorModel,
      limit: Math.min(limit, 50),
-      datasetIds: [datasetId]
+      datasetIds: [datasetId],
+      rerank
    });

    // push bill
--- a/projects/app/src/pages/app/detail/components/BasicEdit/index.tsx
+++ b/projects/app/src/pages/app/detail/components/BasicEdit/index.tsx
@@ -52,7 +52,7 @@ import MyIcon from '@/components/Icon';
 import ChatBox, { type ComponentRef, type StartChatFnProps } from '@/components/ChatBox';

 import { addVariable } from '@/components/core/module/VariableEditModal';
-import { KbParamsModal } from '@/components/core/module/DatasetSelectModal';
+import { DatasetParamsModal } from '@/components/core/module/DatasetSelectModal';
 import { AppTypeEnum } from '@fastgpt/global/core/app/constants';
 import { useDatasetStore } from '@/web/core/dataset/store/dataset';
 import { useAppStore } from '@/web/core/app/store/useAppStore';
@@ -585,15 +585,15 @@ const Settings = ({ appId }: { appId: string }) => {
      )}

      {isOpenKbParams && (
-        <KbParamsModal
-          searchEmptyText={getValues('dataset.searchEmptyText')}
-          searchLimit={getValues('dataset.searchLimit')}
-          searchSimilarity={getValues('dataset.searchSimilarity')}
+        <DatasetParamsModal
+          {...getValues('dataset')}
          onClose={onCloseKbParams}
-          onChange={({ searchEmptyText, searchLimit, searchSimilarity }) => {
-            setValue('dataset.searchEmptyText', searchEmptyText);
-            setValue('dataset.searchLimit', searchLimit);
-            setValue('dataset.searchSimilarity', searchSimilarity);
+          onChange={(e) => {
+            setValue('dataset', {
+              ...getValues('dataset'),
+              ...e
+            });
+
            setRefresh((state) => !state);
          }}
        />
--- a/projects/app/src/pages/dataset/detail/components/Test.tsx
+++ b/projects/app/src/pages/dataset/detail/components/Test.tsx
@@ -1,5 +1,5 @@
 import React, { useEffect, useMemo, useState } from 'react';
-import { Box, Textarea, Button, Flex, useTheme, Grid, Progress } from '@chakra-ui/react';
+import { Box, Textarea, Button, Flex, useTheme, Grid, Progress, Switch } from '@chakra-ui/react';
 import { useDatasetStore } from '@/web/core/dataset/store/dataset';
 import { useSearchTestStore, SearchTestStoreItemType } from '@/web/core/dataset/store/searchTest';
 import { getDatasetDataItemById, postSearchText } from '@/web/core/dataset/api';
@@ -15,6 +15,7 @@ import MyTooltip from '@/components/MyTooltip';
 import { QuestionOutlineIcon } from '@chakra-ui/icons';
 import { SearchDataResponseItemType } from '@fastgpt/global/core/dataset/type';
 import { useTranslation } from 'next-i18next';
+import { feConfigs } from '@/web/common/system/staticData';
 const nanoid = customAlphabet('abcdefghijklmnopqrstuvwxyz1234567890', 12);

 const Test = ({ datasetId }: { datasetId: string }) => {
@@ -28,6 +29,7 @@ const Test = ({ datasetId }: { datasetId: string }) => {
  const [inputText, setInputText] = useState('');
  const [datasetTestItem, setDatasetTestItem] = useState<SearchTestStoreItemType>();
  const [editInputData, setEditInputData] = useState<InputDataType & { collectionId: string }>();
+  const [rerank, setRerank] = useState(false);

  const kbTestHistory = useMemo(
    () => datasetTestList.filter((item) => item.datasetId === datasetId),
@@ -35,7 +37,7 @@ const Test = ({ datasetId }: { datasetId: string }) => {
  );

  const { mutate, isLoading } = useRequest({
-    mutationFn: () => postSearchText({ datasetId, text: inputText.trim() }),
+    mutationFn: () => postSearchText({ datasetId, text: inputText.trim(), rerank, limit: 20 }),
    onSuccess(res: SearchDataResponseItemType[]) {
      if (!res || res.length === 0) {
        return toast({
@@ -91,7 +93,13 @@ const Test = ({ datasetId }: { datasetId: string }) => {
            onChange={(e) => setInputText(e.target.value)}
          />
          <Flex alignItems={'center'} justifyContent={'flex-end'}>
-            <Box mr={3} color={'myGray.500'}>
+            {feConfigs?.isPlus && (
+              <Flex alignItems={'center'}>
+                {t('dataset.recall.rerank')}
+                <Switch ml={1} isChecked={rerank} onChange={(e) => setRerank(e.target.checked)} />
+              </Flex>
+            )}
+            <Box mx={3} color={'myGray.500'}>
              {inputText.length}
            </Box>
            <Button isDisabled={inputText === ''} isLoading={isLoading} onClick={mutate}>
--- a/projects/app/src/service/core/dataset/data/pg.ts
+++ b/projects/app/src/service/core/dataset/data/pg.ts
@@ -131,13 +131,15 @@ export async function searchDatasetData({
  model,
  similarity = 0,
  limit,
-  datasetIds = []
+  datasetIds = [],
+  rerank = false
 }: {
  text: string;
  model: string;
  similarity?: number; // min distance
  limit: number;
  datasetIds: string[];
+  rerank?: boolean;
 }) {
  const { vectors, tokenLen } = await getVectorsByText({
    model,
@@ -219,6 +221,13 @@ export async function searchDatasetData({
    return true;
  });

+  if (!rerank) {
+    return {
+      searchRes: filterData.slice(0, limit),
+      tokenLen
+    };
+  }
+
  // ReRank result
  const reRankResult = await reRankSearchResult({
    query: text,
--- a/projects/app/src/service/moduleDispatch/chat/oneapi.ts
+++ b/projects/app/src/service/moduleDispatch/chat/oneapi.ts
@@ -208,7 +208,7 @@ function filterQuote({
      source: item.sourceName,
      sourceId: String(item.sourceId || 'UnKnow'),
      index: index + 1,
-      score: item.score.toFixed(4)
+      score: item.score?.toFixed(4)
    });
  }
  const sliceResult = sliceMessagesTB({
--- a/projects/app/src/service/moduleDispatch/dataset/search.ts
+++ b/projects/app/src/service/moduleDispatch/dataset/search.ts
@@ -11,6 +11,7 @@ type DatasetSearchProps = ModuleDispatchProps<{
  datasets: SelectedDatasetType;
  similarity: number;
  limit: number;
+  rerank: boolean;
  userChatInput: string;
 }>;
 export type KBSearchResponse = {
@@ -20,9 +21,9 @@ export type KBSearchResponse = {
  quoteQA: SearchDataResponseItemType[];
 };

-export async function dispatchDatasetSearch(props: Record<string, any>): Promise<KBSearchResponse> {
+export async function dispatchDatasetSearch(props: DatasetSearchProps): Promise<KBSearchResponse> {
  const {
-    inputs: { datasets = [], similarity = 0.4, limit = 5, userChatInput }
+    inputs: { datasets = [], similarity = 0.4, limit = 5, rerank, userChatInput }
  } = props as DatasetSearchProps;

  if (datasets.length === 0) {
@@ -41,7 +42,8 @@ export async function dispatchDatasetSearch(props: Record<string, any>): Promise
    model: vectorModel.model,
    similarity,
    limit,
-    datasetIds: datasets.map((item) => item.datasetId)
+    datasetIds: datasets.map((item) => item.datasetId),
+    rerank
  });

  return {
--- a/projects/app/src/web/common/api/fetch.ts
+++ b/projects/app/src/web/common/api/fetch.ts
@@ -95,12 +95,13 @@ export const streamFetch = ({
          });
          read();
        } catch (err: any) {
-          if (err?.message === 'The user aborted a request.') {
+          if (abortSignal.signal.aborted) {
            return resolve({
              responseText,
              responseData
            });
          }
+
          reject({
            responseText,
            message: getErrText(err, '请求异常')
--- a/projects/app/src/web/core/app/basicSettings.ts
+++ b/projects/app/src/web/core/app/basicSettings.ts
@@ -20,6 +20,7 @@ export type EditFormType = {
    searchSimilarity: number;
    searchLimit: number;
    searchEmptyText: string;
+    rerank: boolean;
  };
  guide: {
    welcome: {
@@ -49,7 +50,8 @@ export const getDefaultAppForm = (): EditFormType => {
      list: [],
      searchSimilarity: 0.4,
      searchLimit: 5,
-      searchEmptyText: ''
+      searchEmptyText: '',
+      rerank: false
    },
    guide: {
      welcome: {
@@ -136,6 +138,11 @@ export const appModules2Form = (modules: ModuleItemType[]) => {
        inputs: module.inputs,
        key: 'limit'
      });
+      updateVal({
+        formKey: 'dataset.rerank',
+        inputs: module.inputs,
+        key: 'rerank'
+      });
      // empty text
      const emptyOutputs = module.outputs.find((item) => item.key === 'isEmpty')?.targets || [];
      const emptyOutput = emptyOutputs[0];
@@ -475,6 +482,15 @@ const kbTemplate = (formData: EditFormType): ModuleItemType[] => [
        type: FlowNodeInputTypeEnum.target,
        label: '用户问题',
        connected: true
+      },
+      {
+        key: 'rerank',
+        type: FlowNodeInputTypeEnum.switch,
+        label: '结果重排',
+        description: '将召回的结果进行进一步重排，可增加召回率',
+        plusField: true,
+        connected: true,
+        value: formData.dataset.rerank
      }
    ],
    outputs: [