estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix overlap and splitter optimization (#2742)

Browse Source 
Co-authored-by: jyong <jyong@dify.ai>
This commit is contained in:
Jyong
2024-03-07 18:25:49 +08:00
committed by GitHub
parent b163545771
commit 8ba38e8e74
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/core/splitter/text_splitter.py
View File

@@ -30,7 +30,7 @@ def _split_text_with_regex(
if separator:
if keep_separator:
# The parentheses in the pattern keep the delimiters in the result.
_splits = re.split(f"({separator})", text)
_splits = re.split(f"({re.escape(separator)})", text)
splits = [_splits[i] + _splits[i + 1] for i in range(1, len(_splits), 2)]
if len(_splits) % 2 == 0:
splits += _splits[-1:]
@@ -94,7 +94,7 @@ class TextSplitter(BaseDocumentTransformer, ABC):
documents.append(new_doc)
return documents
def split_documents(self, documents: Iterable[Document]) -> list[Document]:
def split_documents(self, documents: Iterable[Document] ) -> list[Document]:
"""Split documents."""
texts, metadatas = [], []
for doc in documents: