diff --git a/poetry.lock b/poetry.lock index 0d685fe3..51688fe6 100644 --- a/poetry.lock +++ b/poetry.lock @@ -864,28 +864,30 @@ name = "docling-core" version = "2.15.1" description = "A python library to define and validate data types in Docling." optional = false -python-versions = "<4.0,>=3.9" -files = [ - {file = "docling_core-2.15.1-py3-none-any.whl", hash = "sha256:33152604e1f14d5caccbef099c73163c3f211d0b4d92403d262c308633cc0451"}, - {file = "docling_core-2.15.1.tar.gz", hash = "sha256:588d941b5bfc393a79e779ab64819c60763e7f182ec5221ee37da4be91dd802f"}, -] +python-versions = "^3.9" +files = [] +develop = false [package.dependencies] -jsonref = ">=1.1.0,<2.0.0" -jsonschema = ">=4.16.0,<5.0.0" -pandas = ">=2.1.4,<3.0.0" -pillow = ">=10.3.0,<11.0.0" -pydantic = ">=2.6.0,<2.10.0 || >2.10.0,<2.10.1 || >2.10.1,<2.10.2 || >2.10.2,<3.0.0" +jsonref = "^1.1.0" +jsonschema = "^4.16.0" +pandas = "^2.1.4" +pillow = "^10.3.0" +pydantic = ">=2.6.0,<3.0.0,!=2.10.0,!=2.10.1,!=2.10.2" pyyaml = ">=5.1,<7.0.0" -semchunk = {version = ">=2.2.0,<3.0.0", optional = true, markers = "extra == \"chunking\""} -tabulate = ">=0.9.0,<0.10.0" -transformers = {version = ">=4.34.0,<5.0.0", optional = true, markers = "extra == \"chunking\""} -typer = ">=0.12.5,<0.13.0" -typing-extensions = ">=4.12.2,<5.0.0" +tabulate = "^0.9.0" +typer = "^0.12.5" +typing-extensions = "^4.12.2" [package.extras] chunking = ["semchunk (>=2.2.0,<3.0.0)", "transformers (>=4.34.0,<5.0.0)"] +[package.source] +type = "git" +url = "https://github.com/DS4SD/docling-core" +reference = "dev/add-geometric-operations-in-boundingbox" +resolved_reference = "22837f9ee86c4d46c2093810e784b5cc5dbf3a14" + [[package]] name = "docling-ibm-models" version = "3.3.0" @@ -2804,32 +2806,6 @@ files = [ {file = "more_itertools-10.6.0-py3-none-any.whl", hash = "sha256:6eb054cb4b6db1473f6e15fcc676a08e4732548acd47c708f0e179c2c7c01e89"}, ] -[[package]] -name = "mpire" -version = "2.10.2" -description = "A Python package for easy multiprocessing, but faster than multiprocessing" -optional = false -python-versions = "*" -files = [ - {file = "mpire-2.10.2-py3-none-any.whl", hash = "sha256:d627707f7a8d02aa4c7f7d59de399dec5290945ddf7fbd36cbb1d6ebb37a51fb"}, - {file = "mpire-2.10.2.tar.gz", hash = "sha256:f66a321e93fadff34585a4bfa05e95bd946cf714b442f51c529038eb45773d97"}, -] - -[package.dependencies] -multiprocess = [ - {version = "*", optional = true, markers = "python_version < \"3.11\" and extra == \"dill\""}, - {version = ">=0.70.15", optional = true, markers = "python_version >= \"3.11\" and extra == \"dill\""}, -] -pygments = ">=2.0" -pywin32 = {version = ">=301", markers = "platform_system == \"Windows\""} -tqdm = ">=4.27" - -[package.extras] -dashboard = ["flask"] -dill = ["multiprocess", "multiprocess (>=0.70.15)"] -docs = ["docutils (==0.17.1)", "sphinx (==3.2.1)", "sphinx-autodoc-typehints (==1.11.0)", "sphinx-rtd-theme (==0.5.0)", "sphinx-versions (==1.0.1)", "sphinxcontrib-images (==0.9.2)"] -testing = ["ipywidgets", "multiprocess", "multiprocess (>=0.70.15)", "numpy", "pywin32 (>=301)", "rich"] - [[package]] name = "mpmath" version = "1.3.0" @@ -3823,10 +3799,10 @@ files = [ numpy = [ {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""}, {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""}, - {version = ">=1.26.0", markers = "python_version >= \"3.12\""}, - {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""}, {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""}, {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""}, + {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""}, + {version = ">=1.26.0", markers = "python_version >= \"3.12\""}, ] [[package]] @@ -3849,10 +3825,10 @@ files = [ numpy = [ {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""}, {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""}, - {version = ">=1.26.0", markers = "python_version >= \"3.12\""}, - {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""}, {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""}, {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""}, + {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""}, + {version = ">=1.26.0", markers = "python_version >= \"3.12\""}, ] [[package]] @@ -4037,8 +4013,8 @@ files = [ [package.dependencies] numpy = [ {version = ">=1.22.4", markers = "python_version < \"3.11\""}, - {version = ">=1.26.0", markers = "python_version >= \"3.12\""}, {version = ">=1.23.2", markers = "python_version == \"3.11\""}, + {version = ">=1.26.0", markers = "python_version >= \"3.12\""}, ] python-dateutil = ">=2.8.2" pytz = ">=2020.1" @@ -6096,21 +6072,6 @@ files = [ cryptography = ">=2.0" jeepney = ">=0.6" -[[package]] -name = "semchunk" -version = "2.2.2" -description = "A fast and lightweight Python library for splitting text into semantically meaningful chunks." -optional = false -python-versions = ">=3.9" -files = [ - {file = "semchunk-2.2.2-py3-none-any.whl", hash = "sha256:94ca19020c013c073abdfd06d79a7c13637b91738335f3b8cdb5655ee7cc94d2"}, - {file = "semchunk-2.2.2.tar.gz", hash = "sha256:940e89896e64eeb01de97ba60f51c8c7b96c6a3951dfcf574f25ce2146752f52"}, -] - -[package.dependencies] -mpire = {version = "*", extras = ["dill"]} -tqdm = "*" - [[package]] name = "semver" version = "2.13.0" @@ -7751,4 +7712,4 @@ tesserocr = ["tesserocr"] [metadata] lock-version = "2.0" python-versions = "^3.9" -content-hash = "08d30cee8d77f9beee32d5dbec1643367ecae2b4c4b47b57fcb337711471eb5c" +content-hash = "fb8f2a4d8229bed7e093c92117ed4d4ea4fbcbaaafddd375357d3d32df0504d5" diff --git a/pyproject.toml b/pyproject.toml index d5ea2955..81c3be9e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -26,7 +26,7 @@ packages = [{include = "docling"}] ###################### python = "^3.9" pydantic = "^2.0.0" -docling-core = { version = "^2.15.1", extras = ["chunking"] } +docling-core = {git = "https://github.com/DS4SD/docling-core", rev = "dev/add-geometric-operations-in-boundingbox"} docling-ibm-models = "^3.3.0" deepsearch-glm = "^1.0.0" docling-parse = "^3.1.0"