langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 12:05:30 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

[PR #4832] Add the ability to parse PDF tables, pictures, and cross-page tables #24660

New Issue
Closed
opened 2026-02-21 20:23:26 -05:00 by yindo · 0 comments
yindo commented 2026-02-21 20:23:26 -05:00
Owner
Copy Link
Copy Source

Original Pull Request: https://github.com/langgenius/dify/pull/4832

State: closed
Merged: No

Description

Using the enhanced open parsing library to parse PDF documents, you can maintain the table style of the PDF document, and also extract image content, table content, cross-page tables, etc. in the PDF, while trying to ensure that it meets the user's reading order.

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

To test the PDF parsing function individually, use the following code, Use pdfmimer algorithm
`from core.rag.extractor.pdf.openparse import DocumentParser, processing
from core.rag.extractor.pdf.openparse.schemas import ImageElement

if name == 'main':
"""Lazy load given path as pages."""
# blob = Blob.from_path(self._file_path)
# yield from self.parse(blob)
file_path = "pdf file path here"
documents = []
parser = DocumentParser(
processing_pipeline=processing.BasicIngestionPipeline(),
table_args={
"parsing_algorithm": "pdfmimer",
"table_output_format": "markdown"
}
)
parsed_basic_doc = parser.parse(file_path)
documentContent = ''
for _index, node in enumerate(parsed_basic_doc.nodes):
metadata = {"source": file_path, "page": _index}
for element in node.elements:
if isinstance(element, ImageElement):
# pdf images a
pass
else:
print(element.text)`

there is ImageElement\ TableElement\TextElement
If you parse the image, the focus is ImageElement， which has the following attributes that can be used
block: dict
text: str
image: bytes
ext: str
bbox: Bbox

**Original Pull Request:** https://github.com/langgenius/dify/pull/4832 **State:** closed **Merged:** No --- # Description Using the enhanced open parsing library to parse PDF documents, you can maintain the table style of the PDF document, and also extract image content, table content, cross-page tables, etc. in the PDF, while trying to ensure that it meets the user's reading order. # How Has This Been Tested? Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration To test the PDF parsing function individually, use the following code, Use pdfmimer algorithm `from core.rag.extractor.pdf.openparse import DocumentParser, processing from core.rag.extractor.pdf.openparse.schemas import ImageElement if __name__ == '__main__': """Lazy load given path as pages.""" # blob = Blob.from_path(self._file_path) # yield from self.parse(blob) file_path = "pdf file path here" documents = [] parser = DocumentParser( processing_pipeline=processing.BasicIngestionPipeline(), table_args={ "parsing_algorithm": "pdfmimer", "table_output_format": "markdown" } ) parsed_basic_doc = parser.parse(file_path) documentContent = '' for _index, node in enumerate(parsed_basic_doc.nodes): metadata = {"source": file_path, "page": _index} for element in node.elements: if isinstance(element, ImageElement): # pdf images a pass else: print(element.text)` there is ImageElement\ TableElement\TextElement If you parse the image, the focus is ImageElement， which has the following attributes that can be used block: dict text: str image: bytes ext: str bbox: Bbox
yindo added the pull-request label 2026-02-21 20:23:26 -05:00
yindo closed this issue 2026-02-21 20:23:26 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#24660
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?