From bf64ff215be9e9094afddbd9523188c78942b039 Mon Sep 17 00:00:00 2001 From: crazywoola <100913391+crazywoola@users.noreply.github.com> Date: Wed, 25 Sep 2024 10:09:20 +0800 Subject: [PATCH] fix: . is missing in file_extension (#8736) --- api/core/rag/extractor/extract_processor.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/api/core/rag/extractor/extract_processor.py b/api/core/rag/extractor/extract_processor.py index fe7eaa32e6..0ffc89b214 100644 --- a/api/core/rag/extractor/extract_processor.py +++ b/api/core/rag/extractor/extract_processor.py @@ -124,7 +124,7 @@ class ExtractProcessor: extractor = UnstructuredPPTXExtractor(file_path, unstructured_api_url) elif file_extension == ".xml": extractor = UnstructuredXmlExtractor(file_path, unstructured_api_url) - elif file_extension == "epub": + elif file_extension == ".epub": extractor = UnstructuredEpubExtractor(file_path, unstructured_api_url) else: # txt @@ -146,7 +146,7 @@ class ExtractProcessor: extractor = WordExtractor(file_path, upload_file.tenant_id, upload_file.created_by) elif file_extension == ".csv": extractor = CSVExtractor(file_path, autodetect_encoding=True) - elif file_extension == "epub": + elif file_extension == ".epub": extractor = UnstructuredEpubExtractor(file_path) else: # txt