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

Feat: add more chunking method (#11413)

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

Feat: add more chunking method #11311

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Billy Bao
2025-11-20 19:07:17 +08:00
committed by GitHub
parent c8ab9079b3
commit d3d2ccc76c
6 changed files with 66 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/app/naive.py
View File

@ -59,6 +59,7 @@ def by_mineru(filename, binary=None, from_page=0, to_page=100000, lang="Chinese"
mineru_executable = os.environ.get("MINERU_EXECUTABLE", "mineru")
mineru_api = os.environ.get("MINERU_APISERVER", "http://host.docker.internal:9987")
pdf_parser = MinerUParser(mineru_path=mineru_executable, mineru_api=mineru_api)
parse_method = kwargs.get("parse_method", "raw")
if not pdf_parser.check_installation():
callback(-1, "MinerU not found.")
@ -72,12 +73,14 @@ def by_mineru(filename, binary=None, from_page=0, to_page=100000, lang="Chinese"
backend=os.environ.get("MINERU_BACKEND", "pipeline"),
server_url=os.environ.get("MINERU_SERVER_URL", ""),
delete_output=bool(int(os.environ.get("MINERU_DELETE_OUTPUT", 1))),
parse_method=parse_method
)
return sections, tables, pdf_parser
def by_docling(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", callback=None, pdf_cls = None ,**kwargs):
pdf_parser = DoclingParser()
parse_method = kwargs.get("parse_method", "raw")
if not pdf_parser.check_installation():
callback(-1, "Docling not found.")
@ -89,6 +92,7 @@ def by_docling(filename, binary=None, from_page=0, to_page=100000, lang="Chinese
callback=callback,
output_dir=os.environ.get("MINERU_OUTPUT_DIR", ""),
delete_output=bool(int(os.environ.get("MINERU_DELETE_OUTPUT", 1))),
parse_method=parse_method
)
return sections, tables, pdf_parser