forked from NixOS/nixpkgs
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
docling: init at 2.17.0 (NixOS#359783)
- Loading branch information
Showing
6 changed files
with
211 additions
and
20 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,3 @@ | ||
| { python3Packages }: | ||
|
|
||
| python3Packages.toPythonApplication python3Packages.docling |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,150 @@ | ||
| { | ||
| lib, | ||
| buildPythonPackage, | ||
| fetchFromGitHub, | ||
| # dependencies | ||
| pydantic, | ||
| docling-core, | ||
| docling-ibm-models, | ||
| deepsearch-glm, | ||
| docling-parse, | ||
| filetype, | ||
| pypdfium2, | ||
| pydantic-settings, | ||
| huggingface-hub, | ||
| requests, | ||
| easyocr, | ||
| tesserocr, | ||
| certifi, | ||
| rtree, | ||
| scipy, | ||
| typer, | ||
| python-docx, | ||
| python-pptx, | ||
| beautifulsoup4, | ||
| pandas, | ||
| marko, | ||
| openpyxl, | ||
| lxml, | ||
| # ocrmac # not yet packaged | ||
| rapidocr-onnxruntime, | ||
| onnxruntime, | ||
| pillow, | ||
| pyarrow, | ||
| # build system | ||
| poetry-core, | ||
| # optional dependencies | ||
| mkdocs-material, | ||
| mkdocs-jupyter, | ||
| # mkdocs-click # not yet packaged | ||
| mkdocstrings, | ||
| # native check inputs | ||
| pytestCheckHook, | ||
| }: | ||
|
|
||
| buildPythonPackage rec { | ||
| pname = "docling"; | ||
| version = "2.17.0"; | ||
| pyproject = true; | ||
|
|
||
| src = fetchFromGitHub { | ||
| owner = "DS4SD"; | ||
| repo = "docling"; | ||
| tag = "v${version}"; | ||
| hash = "sha256-OtUFQRNqyTGT1Z41tHziwM5hqbk+tg/97bxhtPVtmN0="; | ||
| }; | ||
|
|
||
| build-system = [ | ||
| poetry-core | ||
| ]; | ||
|
|
||
| dependencies = [ | ||
| pydantic | ||
| docling-core | ||
| docling-ibm-models | ||
| deepsearch-glm | ||
| docling-parse | ||
| filetype | ||
| pypdfium2 | ||
| pydantic-settings | ||
| huggingface-hub | ||
| requests | ||
| easyocr | ||
| tesserocr | ||
| certifi | ||
| rtree | ||
| scipy | ||
| typer | ||
| python-docx | ||
| python-pptx | ||
| beautifulsoup4 | ||
| pandas | ||
| marko | ||
| openpyxl | ||
| lxml | ||
| # ocrmac # not yet packaged | ||
| rapidocr-onnxruntime | ||
| onnxruntime | ||
| pillow | ||
| pyarrow | ||
| ]; | ||
|
|
||
| pythonRelaxDeps = [ | ||
| "pillow" | ||
| ]; | ||
|
|
||
| optional-dependencies = { | ||
| ocrmac = [ | ||
| # ocrmac # not yet packaged | ||
| ]; | ||
| rapidocr = [ | ||
| onnxruntime | ||
| rapidocr-onnxruntime | ||
| ]; | ||
| tesserocr = [ | ||
| tesserocr | ||
| ]; | ||
|
|
||
| docs = [ | ||
| mkdocs-material | ||
| mkdocs-jupyter | ||
| # mkdocs-click # not yet packaged | ||
| mkdocstrings | ||
| # griffle-pydantic | ||
| ]; | ||
| }; | ||
|
|
||
| preCheck = '' | ||
| export HOME="$TEMPDIR" | ||
| ''; | ||
|
|
||
| nativeCheckInputs = [ | ||
| pytestCheckHook | ||
| ]; | ||
|
|
||
| pythonImportsCheck = [ | ||
| "docling" | ||
| ]; | ||
|
|
||
| disabledTests = [ | ||
| "test_e2e_pdfs_conversions" # AssertionError: ## TableFormer: Table Structure Understanding with Transf | ||
| "test_e2e_conversions" # RuntimeError: Tesseract is not available | ||
| # huggingface_hub.errors.LocalEntryNotFoundError: An error happened | ||
| "test_cli_convert" | ||
| "test_code_and_formula_conversion" | ||
| "test_picture_classifier" | ||
| "test_convert_path" | ||
| "test_convert_stream" | ||
| "test_compare_legacy_output" | ||
| "test_ocr_coverage_threshold" | ||
| ]; | ||
|
|
||
| meta = { | ||
| description = "Get your documents ready for gen AI"; | ||
| homepage = "https://github.com/DS4SD/docling"; | ||
| changelog = "https://github.com/DS4SD/docling/blob/${src.rev}/CHANGELOG.md"; | ||
| license = lib.licenses.mit; | ||
| maintainers = with lib.maintainers; [ happysalada ]; | ||
| mainProgram = "docling"; | ||
| }; | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters