diff --git a/poetry.lock b/poetry.lock index 363f9b2e..cedeb768 100644 --- a/poetry.lock +++ b/poetry.lock @@ -759,13 +759,37 @@ vision = ["Pillow (>=9.4.0)"] [[package]] name = "debugpy" -version = "1.8.10" +version = "1.8.9" description = "An implementation of the Debug Adapter Protocol for Python" optional = false python-versions = ">=3.8" files = [ - {file = "debugpy-1.8.10-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:97aa00af95983887806e06f37e144909d35215d66db74f8b0e9799b4eef40cfd"}, - {file = "debugpy-1.8.10.tar.gz", hash = "sha256:ee4ed903cbeb14ee1839549f953af519ffa512598ec987b2051f9c868e2249a8"}, + {file = "debugpy-1.8.9-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:cfe1e6c6ad7178265f74981edf1154ffce97b69005212fbc90ca22ddfe3d017e"}, + {file = "debugpy-1.8.9-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ada7fb65102a4d2c9ab62e8908e9e9f12aed9d76ef44880367bc9308ebe49a0f"}, + {file = "debugpy-1.8.9-cp310-cp310-win32.whl", hash = "sha256:c36856343cbaa448171cba62a721531e10e7ffb0abff838004701454149bc037"}, + {file = "debugpy-1.8.9-cp310-cp310-win_amd64.whl", hash = "sha256:17c5e0297678442511cf00a745c9709e928ea4ca263d764e90d233208889a19e"}, + {file = "debugpy-1.8.9-cp311-cp311-macosx_14_0_universal2.whl", hash = "sha256:b74a49753e21e33e7cf030883a92fa607bddc4ede1aa4145172debc637780040"}, + {file = "debugpy-1.8.9-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:62d22dacdb0e296966d7d74a7141aaab4bec123fa43d1a35ddcb39bf9fd29d70"}, + {file = "debugpy-1.8.9-cp311-cp311-win32.whl", hash = "sha256:8138efff315cd09b8dcd14226a21afda4ca582284bf4215126d87342bba1cc66"}, + {file = "debugpy-1.8.9-cp311-cp311-win_amd64.whl", hash = "sha256:ff54ef77ad9f5c425398efb150239f6fe8e20c53ae2f68367eba7ece1e96226d"}, + {file = "debugpy-1.8.9-cp312-cp312-macosx_14_0_universal2.whl", hash = "sha256:957363d9a7a6612a37458d9a15e72d03a635047f946e5fceee74b50d52a9c8e2"}, + {file = "debugpy-1.8.9-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e565fc54b680292b418bb809f1386f17081d1346dca9a871bf69a8ac4071afe"}, + {file = "debugpy-1.8.9-cp312-cp312-win32.whl", hash = "sha256:3e59842d6c4569c65ceb3751075ff8d7e6a6ada209ceca6308c9bde932bcef11"}, + {file = "debugpy-1.8.9-cp312-cp312-win_amd64.whl", hash = "sha256:66eeae42f3137eb428ea3a86d4a55f28da9bd5a4a3d369ba95ecc3a92c1bba53"}, + {file = "debugpy-1.8.9-cp313-cp313-macosx_14_0_universal2.whl", hash = "sha256:957ecffff80d47cafa9b6545de9e016ae8c9547c98a538ee96ab5947115fb3dd"}, + {file = "debugpy-1.8.9-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1efbb3ff61487e2c16b3e033bc8595aea578222c08aaf3c4bf0f93fadbd662ee"}, + {file = "debugpy-1.8.9-cp313-cp313-win32.whl", hash = "sha256:7c4d65d03bee875bcb211c76c1d8f10f600c305dbd734beaed4077e902606fee"}, + {file = "debugpy-1.8.9-cp313-cp313-win_amd64.whl", hash = "sha256:e46b420dc1bea64e5bbedd678148be512442bc589b0111bd799367cde051e71a"}, + {file = "debugpy-1.8.9-cp38-cp38-macosx_14_0_x86_64.whl", hash = "sha256:472a3994999fe6c0756945ffa359e9e7e2d690fb55d251639d07208dbc37caea"}, + {file = "debugpy-1.8.9-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:365e556a4772d7d0d151d7eb0e77ec4db03bcd95f26b67b15742b88cacff88e9"}, + {file = "debugpy-1.8.9-cp38-cp38-win32.whl", hash = "sha256:54a7e6d3014c408eb37b0b06021366ee985f1539e12fe49ca2ee0d392d9ceca5"}, + {file = "debugpy-1.8.9-cp38-cp38-win_amd64.whl", hash = "sha256:8e99c0b1cc7bf86d83fb95d5ccdc4ad0586d4432d489d1f54e4055bcc795f693"}, + {file = "debugpy-1.8.9-cp39-cp39-macosx_14_0_x86_64.whl", hash = "sha256:7e8b079323a56f719977fde9d8115590cb5e7a1cba2fcee0986ef8817116e7c1"}, + {file = "debugpy-1.8.9-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6953b335b804a41f16a192fa2e7851bdcfd92173cbb2f9f777bb934f49baab65"}, + {file = "debugpy-1.8.9-cp39-cp39-win32.whl", hash = "sha256:7e646e62d4602bb8956db88b1e72fe63172148c1e25c041e03b103a25f36673c"}, + {file = "debugpy-1.8.9-cp39-cp39-win_amd64.whl", hash = "sha256:3d9755e77a2d680ce3d2c5394a444cf42be4a592caaf246dbfbdd100ffcf7ae5"}, + {file = "debugpy-1.8.9-py2.py3-none-any.whl", hash = "sha256:cc37a6c9987ad743d9c3a14fa1b1a14b7e4e6041f9dd0c8abf8895fe7a97b899"}, + {file = "debugpy-1.8.9.zip", hash = "sha256:1339e14c7d980407248f09824d1b25ff5c5616651689f1e0f0e51bdead3ea13e"}, ] [[package]] @@ -867,27 +891,29 @@ name = "docling-core" version = "2.9.0" description = "A python library to define and validate data types in Docling." optional = false -python-versions = "<4.0,>=3.9" -files = [ - {file = "docling_core-2.9.0-py3-none-any.whl", hash = "sha256:b44b077db5d2ac8a900f30a15abe329c165b1f2eb7f1c90d1275c423c1c3d668"}, - {file = "docling_core-2.9.0.tar.gz", hash = "sha256:1bf12fe67ee4852330e9bac33fe62b45598ff885481e03a88fa8e1bf48252424"}, -] +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\""} -typing-extensions = ">=4.12.2,<5.0.0" +tabulate = "^0.9.0" +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 = "ssh://git@github.com/DS4SD/docling-core.git" +reference = "improve-doc-item-typing" +resolved_reference = "948a1c56caef3fe1770d7c5cdc61cbf9bc026113" + [[package]] name = "docling-ibm-models" version = "3.0.0" @@ -2796,32 +2822,6 @@ files = [ {file = "more_itertools-10.5.0-py3-none-any.whl", hash = "sha256:037b0d3203ce90cca8ab1defbbdac29d5f993fc20131f3664dc8d6acfa872aef"}, ] -[[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" @@ -5482,12 +5482,12 @@ cffi = {version = "*", markers = "implementation_name == \"pypy\""} [[package]] name = "rapidocr-onnxruntime" -version = "1.4.2" +version = "1.4.3" description = "A cross platform OCR Library based on OnnxRuntime." optional = true python-versions = "<3.13,>=3.6" files = [ - {file = "rapidocr_onnxruntime-1.4.2-py3-none-any.whl", hash = "sha256:b921eea8cc8f203588e851d2f26e3ab5e8e9d7c7eec2fe3f7a264ae6275d7e28"}, + {file = "rapidocr_onnxruntime-1.4.3-py3-none-any.whl", hash = "sha256:d504fa0e7b1d907818f734dc87e4c98acc4c3feb814a732ad35dda8c03a671bd"}, ] [package.dependencies] @@ -6132,21 +6132,6 @@ files = [ cryptography = ">=2.0" jeepney = ">=0.6" -[[package]] -name = "semchunk" -version = "2.2.0" -description = "A fast and lightweight Python library for splitting text into semantically meaningful chunks." -optional = false -python-versions = ">=3.9" -files = [ - {file = "semchunk-2.2.0-py3-none-any.whl", hash = "sha256:7db19ca90ddb48f99265e789e07a7bb111ae25185f9cc3d44b94e1e61b9067fc"}, - {file = "semchunk-2.2.0.tar.gz", hash = "sha256:4de761ce614036fa3bea61adbe47e3ade7c96ac9b062f223b3ac353dbfd26743"}, -] - -[package.dependencies] -mpire = {version = "*", extras = ["dill"]} -tqdm = "*" - [[package]] name = "semver" version = "2.13.0" @@ -7588,4 +7573,4 @@ tesserocr = ["tesserocr"] [metadata] lock-version = "2.0" python-versions = "^3.9" -content-hash = "4b3ccc0f6fa8a57da342674fa938be59e453a6289d230791c1a5d970ea4441de" +content-hash = "c81c99b768cfca5c58c7d41c553110bad65b16c6f527c4d3892a916dffc47a05" diff --git a/pyproject.toml b/pyproject.toml index f1b18908..653bcd73 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -28,8 +28,8 @@ python = "^3.9" docling-ibm-models = "^3.0.0" deepsearch-glm = "^1.0.0" docling-parse = "^3.0.0" -docling-core = { version = "^2.9.0", extras = ["chunking"] } -#docling-core = { git = "ssh://git@github.com/DS4SD/docling-core.git", branch = "cau/include-picture-contents" } +#docling-core = { version = "^2.9.0", extras = ["chunking"] } +docling-core = { git = "ssh://git@github.com/DS4SD/docling-core.git", branch = "improve-doc-item-typing" } pydantic = "^2.0.0" filetype = "^1.2.0" pypdfium2 = "^4.30.0"