From 23ef2262bd4b0166259a429e5c76630450b8d699 Mon Sep 17 00:00:00 2001 From: "lisaifei@cvte.com" Date: Wed, 21 Jun 2023 11:25:52 +0800 Subject: [PATCH] fix: filter empty value in xlsx to improve vector similarity hit (#422) --- api/core/index/readers/xlsx_parser.py | 4 +++- .../datasets/(datasetDetailLayout)/[datasetId]/layout.tsx | 2 +- web/app/components/datasets/hit-testing/index.tsx | 3 ++- 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/api/core/index/readers/xlsx_parser.py b/api/core/index/readers/xlsx_parser.py index 6062e2ef3e..6b38a1bf16 100644 --- a/api/core/index/readers/xlsx_parser.py +++ b/api/core/index/readers/xlsx_parser.py @@ -27,5 +27,7 @@ class XLSXParser(BaseParser): if keys == []: keys = list(map(str, row)) else: - data.append(json.dumps(dict(zip(keys, list(map(str, row)))), ensure_ascii=False)) + row_dict = dict(zip(keys, row)) + row_dict = {k: v for k, v in row_dict.items() if v} + data.append(json.dumps(row_dict, ensure_ascii=False)) return '\n\n'.join(data) diff --git a/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx b/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx index 2db9b7083f..2ed48d1653 100644 --- a/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx +++ b/web/app/(commonLayout)/datasets/(datasetDetailLayout)/[datasetId]/layout.tsx @@ -124,7 +124,7 @@ const DatasetDetailLayout: FC = (props) => { ? ( <>
{relatedApps?.total || '--'} {t('common.datasetMenus.relatedApp')}
- {relatedApps?.data?.map(item => ())} + {relatedApps?.data?.map((item, index) => ())} ) : ( diff --git a/web/app/components/datasets/hit-testing/index.tsx b/web/app/components/datasets/hit-testing/index.tsx index fae98b7cef..ac510b11ea 100644 --- a/web/app/components/datasets/hit-testing/index.tsx +++ b/web/app/components/datasets/hit-testing/index.tsx @@ -137,8 +137,9 @@ const HitTesting: FC = ({ datasetId }: Props) => {
{t('datasetHitTesting.hit.title')}
- {hitResult?.records.map((record) => { + {hitResult?.records.map((record, idx) => { return