perf: Clean up resources with docling-parse v4, no parsed_page output by default (#2105)

* Call PdfDocument.unload_pages from the pipelines where needed, delete parsed_page data unless requested to keep

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* pin docling-parse and update lock

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Reinstate pipeline_options.generate_parsed_page

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2025-08-20 10:46:31 +02:00
committed by GitHub
parent c5f2e2fdd6
commit 5f57ff2a45
8 changed files with 110 additions and 65 deletions

View File

@@ -45,7 +45,7 @@ requires-python = '>=3.9,<4.0'
dependencies = [
'pydantic (>=2.0.0,<3.0.0)',
'docling-core[chunking] (>=2.42.0,<3.0.0)',
'docling-parse (>=4.0.0,<5.0.0)',
'docling-parse (>=4.2.2,<5.0.0)',
"docling-ibm-models>=3.9.0,<4",
'filetype (>=1.2.0,<2.0.0)',
'pypdfium2 (>=4.30.0,!=4.30.1,<5.0.0)',