RYDE-WORK/Langchain-Chatchat
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/Langchain-Chatchat.git synced 2026-02-06 23:15:53 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update text splitter unit test name

Browse Source
This commit is contained in:
imClumsyPanda 2023-09-13 15:53:07 +08:00
parent f75812afcb
commit dc413120e2
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
tests/custom_splitter/test_different_splitter.py
View File

@ -13,8 +13,11 @@ import langchain.document_loaders
import importlib import importlib
def test_different_splitter(splitter_name, chunk_size: int = CHUNK_SIZE, def test_different_splitter(
chunk_overlap: int = OVERLAP_SIZE, ): splitter_name,
chunk_size: int = CHUNK_SIZE,
chunk_overlap: int = OVERLAP_SIZE,
):
if splitter_name == "MarkdownHeaderTextSplitter": # MarkdownHeaderTextSplitter特殊判定 if splitter_name == "MarkdownHeaderTextSplitter": # MarkdownHeaderTextSplitter特殊判定
headers_to_split_on = text_splitter_dict[splitter_name]['headers_to_split_on'] headers_to_split_on = text_splitter_dict[splitter_name]['headers_to_split_on']
text_splitter = langchain.text_splitter.MarkdownHeaderTextSplitter( text_splitter = langchain.text_splitter.MarkdownHeaderTextSplitter(
@ -72,7 +75,7 @@ if __name__ == "__main__":
filepath = "../../knowledge_base/samples/content/test.txt" filepath = "../../knowledge_base/samples/content/test.txt"
loader = document_loaders.UnstructuredFileLoader(filepath, autodetect_encoding=True) loader = document_loaders.UnstructuredFileLoader(filepath, autodetect_encoding=True)
docs = loader.load() 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 # 使用text_splitter进行分词
if TEXT_SPLITTER_NAME == "MarkdownHeaderTextSplitter": if TEXT_SPLITTER_NAME == "MarkdownHeaderTextSplitter":