From fa7ba30ba3c1612cccf4af0605a48ae20c4dab1a Mon Sep 17 00:00:00 2001 From: "Charlie.Wei" Date: Wed, 6 Mar 2024 11:33:32 +0800 Subject: [PATCH] Fix rebuild index&csv parsing (#2705) Co-authored-by: luowei Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> --- api/core/indexing_runner.py | 2 +- api/core/rag/extractor/csv_extractor.py | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/api/core/indexing_runner.py b/api/core/indexing_runner.py index f5ea49bb5e..abf21b84f5 100644 --- a/api/core/indexing_runner.py +++ b/api/core/indexing_runner.py @@ -186,7 +186,7 @@ class IndexingRunner: first() index_type = dataset_document.doc_form - index_processor = IndexProcessorFactory(index_type, processing_rule.to_dict()).init_index_processor() + index_processor = IndexProcessorFactory(index_type).init_index_processor() self._load( index_processor=index_processor, dataset=dataset, diff --git a/api/core/rag/extractor/csv_extractor.py b/api/core/rag/extractor/csv_extractor.py index c391d7ae66..a8077971dc 100644 --- a/api/core/rag/extractor/csv_extractor.py +++ b/api/core/rag/extractor/csv_extractor.py @@ -3,6 +3,7 @@ import csv from typing import Optional from core.rag.extractor.extractor_base import BaseExtractor +from core.rag.extractor.helpers import detect_file_encodings from core.rag.models.document import Document @@ -36,7 +37,7 @@ class CSVExtractor(BaseExtractor): docs = self._read_from_file(csvfile) except UnicodeDecodeError as e: if self._autodetect_encoding: - detected_encodings = detect_filze_encodings(self._file_path) + detected_encodings = detect_file_encodings(self._file_path) for encoding in detected_encodings: try: with open(self._file_path, newline="", encoding=encoding.encoding) as csvfile: