mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Properly propagating image data per page, together with predicted tags in VLM pipeline. This enables correct figure extraction and page numbers in provenances

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak
2025-01-13 15:21:19 +01:00
parent 01c46e24b1
commit 61bb9dbba2
2 changed files with 229 additions and 218 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/examples/minimal_smol_docling.py
View File

@@ -6,10 +6,11 @@ from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.pipeline.vlm_pipeline import VlmPipeline
# source = "https://arxiv.org/pdf/2408.09869" # document per local path or URL
source = "https://arxiv.org/pdf/2408.09869" # document per local path or URL
# source = "tests/data/2305.03393v1-pg9-img.png"
source = "tests/data/2305.03393v1-pg9.pdf"
# source = "page.png"
# source = "tests/data/2305.03393v1-pg9.pdf"
# source = "demo_data/page.png"
# source = "demo_data/original_tables.pdf"
pipeline_options = PdfPipelineOptions()
pipeline_options.generate_page_images = True