pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: better_handle_different_types (#8775)

Browse Source 
### What problem does this PR solve?


https://github.com/infiniflow/ragflow/issues/8719#issuecomment-3055883271

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Stephen Hu
2025-07-11 18:21:39 +08:00
committed by GitHub
parent bc0cc8559a
commit f569401398
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
rag/nlp/__init__.py
View File

@ -589,17 +589,21 @@ def naive_merge_with_images(texts, images, chunk_token_num=128, delimiter="\n。
dels = get_delimiters(delimiter) dels = get_delimiters(delimiter)
for text, image in zip(texts, images): for text, image in zip(texts, images):
splited_sec = re.split(r"(%s)" % dels, text)
for sub_sec in splited_sec:
if re.match(f"^{dels}$", sub_sec):
continue
# if text is tuple, unpack it # if text is tuple, unpack it
if isinstance(text, tuple): if isinstance(text, tuple):
text_str = text[0] text_str = text[0]
text_pos = text[1] if len(text) > 1 else "" text_pos = text[1] if len(text) > 1 else ""
add_chunk(text_str, image, text_pos) splited_sec = re.split(r"(%s)" % dels, text_str)
for sub_sec in splited_sec:
if re.match(f"^{dels}$", sub_sec):
continue
add_chunk(sub_sec, image, text_pos)
else: else:
add_chunk(text, image) splited_sec = re.split(r"(%s)" % dels, text)
for sub_sec in splited_sec:
if re.match(f"^{dels}$", sub_sec):
continue
add_chunk(sub_sec, image)
return cks, result_images return cks, result_images