opensource
/
dify
mirror of https://github.com/langgenius/dify.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix chunks 2 (#26623) 

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
znn 2025-10-10 13:31:33 +05:30 committed by GitHub
parent aa51662d98
commit 2b6882bd97
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
api/core/rag/splitter/fixed_text_splitter.py
View File

@ -2,6 +2,7 @@
from __future__ import annotations
import re
from typing import Any
from core.model_manager import ModelInstance
@ -52,7 +53,7 @@ class FixedRecursiveCharacterTextSplitter(EnhanceRecursiveCharacterTextSplitter)
"""Create a new TextSplitter."""
super().__init__(**kwargs)
self._fixed_separator = fixed_separator
self._separators = separators or ["\n\n", "\n", " ", ""]
self._separators = separators or ["\n\n", "\n", "。", ". ", " ", ""]
def split_text(self, text: str) -> list[str]:
"""Split incoming text and return chunks."""
@ -90,16 +91,19 @@ class FixedRecursiveCharacterTextSplitter(EnhanceRecursiveCharacterTextSplitter)
# Now that we have the separator, split the text
if separator:
if separator == " ":
splits = text.split()
splits = re.split(r" +", text)
else:
splits = text.split(separator)
splits = [item + separator if i < len(splits) else item for i, item in enumerate(splits)]
else:
splits = list(text)
splits = [s for s in splits if (s not in {"", "\n"})]
if separator == "\n":
splits = [s for s in splits if s != ""]
else:
splits = [s for s in splits if (s not in {"", "\n"})]
_good_splits = []
_good_splits_lengths = [] # cache the lengths of the splits
_separator = "" if self._keep_separator else separator
_separator = separator if self._keep_separator else ""
s_lens = self._length_function(splits)
if separator != "":
for s, s_len in zip(splits, s_lens):