mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-23 15:06:50 +08:00
Fix: model not authorized (#12001)
### What problem does this PR solve? Fix model not authorized. #11973. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
@ -26,6 +26,7 @@ from rag.nlp import bullets_category, remove_contents_table, \
|
||||
from rag.nlp import rag_tokenizer, Node
|
||||
from deepdoc.parser import PdfParser, DocxParser, HtmlParser
|
||||
from rag.app.naive import by_plaintext, PARSERS
|
||||
from common.parser_config_utils import normalize_layout_recognizer
|
||||
|
||||
|
||||
|
||||
@ -155,7 +156,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
|
||||
return tokenize_chunks(chunks, doc, eng, None)
|
||||
|
||||
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
|
||||
layout_recognizer = parser_config.get("layout_recognize", "DeepDOC")
|
||||
layout_recognizer, parser_model_name = normalize_layout_recognizer(
|
||||
parser_config.get("layout_recognize", "DeepDOC")
|
||||
)
|
||||
|
||||
if isinstance(layout_recognizer, bool):
|
||||
layout_recognizer = "DeepDOC" if layout_recognizer else "Plain Text"
|
||||
@ -173,6 +176,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
|
||||
callback = callback,
|
||||
pdf_cls = Pdf,
|
||||
layout_recognizer = layout_recognizer,
|
||||
mineru_llm_name=parser_model_name,
|
||||
**kwargs
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user