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: presentation of PDF using vlm. (#8133)

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

#8109

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-06-09 15:01:52 +08:00
committed by GitHub
parent 4649accd54
commit 24625e0695
1 changed files with 17 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
rag/app/presentation.py
View File

@ -20,6 +20,9 @@ from io import BytesIO
from PIL import Image from PIL import Image
from api.db import LLMType
from api.db.services.llm_service import LLMBundle
from deepdoc.parser.pdf_parser import VisionParser
from rag.nlp import tokenize, is_english from rag.nlp import tokenize, is_english
from rag.nlp import rag_tokenizer from rag.nlp import rag_tokenizer
from deepdoc.parser import PdfParser, PptParser, PlainParser from deepdoc.parser import PdfParser, PptParser, PlainParser
@ -123,11 +126,21 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
res.append(d) res.append(d)
return res return res
elif re.search(r"\.pdf$", filename, re.IGNORECASE): elif re.search(r"\.pdf$", filename, re.IGNORECASE):
layout_recognizer = kwargs.get("layout_recognize", "DeepDOC")
if layout_recognizer == "DeepDOC":
pdf_parser = Pdf() pdf_parser = Pdf()
if kwargs.get("layout_recognize", "DeepDOC") == "Plain Text": sections = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback)
elif layout_recognizer == "Plain Text":
pdf_parser = PlainParser() pdf_parser = PlainParser()
for pn, (txt, img) in enumerate(pdf_parser(filename, binary, sections, _ = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback)
from_page=from_page, to_page=to_page, callback=callback)): else:
vision_model = LLMBundle(kwargs["tenant_id"], LLMType.IMAGE2TEXT, llm_name=layout_recognizer, lang=lang)
pdf_parser = VisionParser(vision_model=vision_model, **kwargs)
sections, _ = pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page,
callback=callback)
callback(0.8, "Finish parsing.")
for pn, (txt, img) in enumerate(sections):
d = copy.deepcopy(doc) d = copy.deepcopy(doc)
pn += from_page pn += from_page
if img: if img: