From dc413120e24a21775e6f1c518751b8eb577f11ea Mon Sep 17 00:00:00 2001 From: imClumsyPanda Date: Wed, 13 Sep 2023 15:53:07 +0800 Subject: [PATCH] update text splitter unit test name --- tests/custom_splitter/test_different_splitter.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tests/custom_splitter/test_different_splitter.py b/tests/custom_splitter/test_different_splitter.py index 1cd8874..5c80cc1 100644 --- a/tests/custom_splitter/test_different_splitter.py +++ b/tests/custom_splitter/test_different_splitter.py @@ -13,8 +13,11 @@ import langchain.document_loaders import importlib -def test_different_splitter(splitter_name, chunk_size: int = CHUNK_SIZE, - chunk_overlap: int = OVERLAP_SIZE, ): +def test_different_splitter( + splitter_name, + chunk_size: int = CHUNK_SIZE, + chunk_overlap: int = OVERLAP_SIZE, +): if splitter_name == "MarkdownHeaderTextSplitter": # MarkdownHeaderTextSplitter特殊判定 headers_to_split_on = text_splitter_dict[splitter_name]['headers_to_split_on'] text_splitter = langchain.text_splitter.MarkdownHeaderTextSplitter( @@ -72,7 +75,7 @@ if __name__ == "__main__": filepath = "../../knowledge_base/samples/content/test.txt" loader = document_loaders.UnstructuredFileLoader(filepath, autodetect_encoding=True) docs = loader.load() - text_splitter = text_different_splitter(TEXT_SPLITTER_NAME, CHUNK_SIZE, OVERLAP_SIZE) + text_splitter = test_different_splitter(TEXT_SPLITTER_NAME, CHUNK_SIZE, OVERLAP_SIZE) # 使用text_splitter进行分词 if TEXT_SPLITTER_NAME == "MarkdownHeaderTextSplitter":