feat: Docling components (#8394)

* initial DoclingComponent

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

* Correct Docling icon style properties.

Signed-off-by: DKL <dkl@zurich.ibm.com>

* add file_path

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

* add load from json and export to various formats

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

* add chunking component

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

* Update src/backend/base/langflow/components/docling/docling_inline.py

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* add Docling Serve component

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

* apply some suggestions

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

* Update src/backend/base/langflow/components/docling/_utils.py

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* Update src/backend/base/langflow/components/docling/docling_remote.py

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* add check for DoclingDocument in list

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

* fix import

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

* add maximum poll timeout and better checks for the retry logic

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

* add updated starter_projects

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

* refactor _get_converter

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

* return only DataFrame

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

* remove LoadDoclingDocument

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

* more options in the chunk component

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

* move docling imports

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

* [autofix.ci] apply automated fixes

* move utils to langflow.base

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

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: DKL <dkl@zurich.ibm.com>
Co-authored-by: DKL <dkl@zurich.ibm.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
Michele Dolfi 2025-06-24 12:54:55 -05:00 • committed by GitHub
commit 6631de2aae
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 1837 additions and 151 deletions

View file

@ -124,6 +124,7 @@ dependencies = [
"cleanlab-tlm>=1.1.2",
'gassist>=0.0.1; sys_platform == "win32"',
"twelvelabs>=0.4.7",
"docling>=2.36.1",
]
[dependency-groups]
@ -219,6 +220,12 @@ postgresql = [
"sqlalchemy[postgresql_psycopg]>=2.0.38,<3.0.0",
]
[tool.uv]
override-dependencies = [
# temporary force a newer python-pptx
"python-pptx>=1.0.2"
]
[project.scripts]
langflow = "langflow.__main__:main"