pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-26 17:16:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Tika server upgrades. (#12073)

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

#12037

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-12-23 09:35:52 +08:00
committed by GitHub
parent a95f22fa88
commit bd76b8ff1a
10 changed files with 52 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/app/manual.py
View File

@ -312,7 +312,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
tk_cnt = num_tokens_from_string(txt)
if sec_id > -1:
last_sid = sec_id
tbls=vision_figure_parser_pdf_wrapper(tbls=tbls,callback=callback,**kwargs)
tbls = vision_figure_parser_pdf_wrapper(tbls=tbls,callback=callback,**kwargs)
res = tokenize_table(tbls, doc, eng)
res.extend(tokenize_chunks(chunks, doc, eng, pdf_parser))
table_ctx = max(0, int(parser_config.get("table_context_size", 0) or 0))
@ -325,7 +325,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
docx_parser = Docx()
ti_list, tbls = docx_parser(filename, binary,
from_page=0, to_page=10000, callback=callback)
tbls=vision_figure_parser_docx_wrapper(sections=ti_list,tbls=tbls,callback=callback,**kwargs)
tbls = vision_figure_parser_docx_wrapper(sections=ti_list,tbls=tbls,callback=callback,**kwargs)
res = tokenize_table(tbls, doc, eng)
for text, image in ti_list:
d = copy.deepcopy(doc)