Fix: change create dataset htto api delimiter default value to r'\n' (#7434)

### What problem does this PR solve?

change create dataset delimiter default value to r'\n'

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
liu an
2025-04-30 17:43:42 +08:00
committed by GitHub
parent fea9d970ec
commit fc379e90d1
4 changed files with 7 additions and 7 deletions

View File

@ -400,7 +400,7 @@ class TestDatasetCreation:
if parser_config is None:
assert res["data"]["parser_config"] == {
"chunk_token_num": 128,
"delimiter": r"\n!?;。;!?",
"delimiter": r"\n",
"html4excel": False,
"layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False},
@ -410,7 +410,7 @@ class TestDatasetCreation:
"auto_keywords": 0,
"auto_questions": 0,
"chunk_token_num": 128,
"delimiter": r"\n!?;。;!?",
"delimiter": r"\n",
"filename_embd_weight": None,
"graphrag": None,
"html4excel": False,

View File

@ -303,7 +303,7 @@ class TestUpdateDocumentParserConfig:
"chunk_token_num": 128,
"layout_recognize": "DeepDOC",
"html4excel": False,
"delimiter": "\\n!?;。;!?",
"delimiter": r"\n",
"task_page_size": 12,
"raptor": {"use_raptor": False},
},
@ -530,7 +530,7 @@ class TestUpdateDocumentParserConfig:
else:
assert res["data"]["docs"][0]["parser_config"] == {
"chunk_token_num": 128,
"delimiter": "\\n!?;。;!?",
"delimiter": r"\n",
"html4excel": False,
"layout_recognize": "DeepDOC",
"raptor": {"use_raptor": False},