mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update test cases for v2

Browse Source
This commit is contained in:
Christoph Auer 2024-10-10 18:51:19 +02:00
commit 7aad3dc946
14 changed files with 282 additions and 590 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docling/datamodel/base_models.py
View File

@ -33,7 +33,13 @@ FormatToMimeType = {
"application/vnd.openxmlformats-officedocument.presentationml.presentation"
},
InputFormat.HTML: {"text/html", "application/xhtml+xml"},
InputFormat.IMAGE: {"image/png", "image/jpeg"},
InputFormat.IMAGE: {
"image/png",
"image/jpeg",
"image/tiff",
"image/gif",
"image/bmp",
},
InputFormat.PDF: {"application/pdf"},
}
MimeTypeToFormat = {

2
examples/run_with_formats.py
View File

@ -25,6 +25,7 @@ input_paths = [
Path("tests/data/lorem_ipsum.docx"),
Path("tests/data/powerpoint_sample.pptx"),
Path("tests/data/2206.01062.pdf"),
# Path("tests/data/2305.03393v1-pg9-img.png"),
]
input = DocumentConversionInput.from_paths(input_paths)
@ -35,6 +36,7 @@ input = DocumentConversionInput.from_paths(input_paths)
doc_converter = DocumentConverter( # all of the below is optional, has internal defaults.
formats=[
InputFormat.PDF,
# InputFormat.IMAGE,
InputFormat.DOCX,
], # whitelist formats, other files are ignored.
format_options={

819
poetry.lock generated
View File

@ -873,7 +873,7 @@ files = [
[[package]]
name = "deepsearch-glm"
version = "0.23.0"
version = "0.24.0"
description = "Graph Language Models"
optional = false
python-versions = "^3.9"
@ -881,16 +881,19 @@ files = []
develop = false
[package.dependencies]
docling-core = {git = "ssh://git@github.com/DS4SD/docling-core.git", rev = "5aa67df483fb82e01ebb8b86433459f86286403f"}
docling-core = {git = "https://github.com/DS4SD/docling-core.git", rev = "e42a1ddf36e53134aef92f0447cc3352a4e82e70"}
docutils = "!=0.21"
matplotlib = "^3.7.1"
networkx = "^3.1"
netwulf = "^0.1.5"
numerize = "^0.12"
numpy = {version = "^1.26.4", markers = "python_version >= \"3.9\""}
pandas = ">=1.5.1"
numpy = [
{version = ">=2.0.2,<3.0.0", markers = "python_version >= \"3.13\""},
{version = ">=1.26.4,<2.0.0", markers = "python_version >= \"3.9\" and python_version < \"3.13\""},
]
pandas = {version = "^2.1.4", markers = "python_version >= \"3.9\""}
python-dotenv = "^1.0.0"
pywin32 = {version = "^306", markers = "sys_platform == \"win32\""}
pywin32 = {version = "^307", markers = "sys_platform == \"win32\""}
requests = "^2.32.3"
rich = "^13.7.0"
tabulate = ">=0.8.9"
@ -901,26 +904,9 @@ toolkit = ["deepsearch-toolkit (>=0.31.0)"]
[package.source]
type = "git"
url = "ssh://git@github.com/DS4SD/deepsearch-glm.git"
reference = "880c6eb50ecdc2c7ec5f3039b257b51cac6199ca"
resolved_reference = "880c6eb50ecdc2c7ec5f3039b257b51cac6199ca"
[[package]]
name = "deprecated"
version = "1.2.14"
description = "Python @deprecated decorator to deprecate old python classes, functions or methods."
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
files = [
{file = "Deprecated-1.2.14-py2.py3-none-any.whl", hash = "sha256:6fac8b097794a90302bdbb17b9b815e732d3c4720583ff1b198499d78470466c"},
{file = "Deprecated-1.2.14.tar.gz", hash = "sha256:e5323eb936458dccc2582dc6f9c322c852a775a27065ff2b0c4970b9d53d01b3"},
]
[package.dependencies]
wrapt = ">=1.10,<2"
[package.extras]
dev = ["PyTest", "PyTest-Cov", "bump2version (<1)", "sphinx (<2)", "tox"]
url = "https://github.com/DS4SD/deepsearch-glm.git"
reference = "a5bcc9fd90d50cc1899da2f878ae8259269ab9bf"
resolved_reference = "a5bcc9fd90d50cc1899da2f878ae8259269ab9bf"
[[package]]
name = "dill"
@ -937,26 +923,15 @@ files = [
graph = ["objgraph (>=1.7.2)"]
profile = ["gprof2dot (>=2022.7.29)"]
[[package]]
name = "dirtyjson"
version = "1.0.8"
description = "JSON decoder for Python that can extract data from the muck"
optional = false
python-versions = "*"
files = [
{file = "dirtyjson-1.0.8-py3-none-any.whl", hash = "sha256:125e27248435a58acace26d5c2c4c11a1c0de0a9c5124c5a94ba78e517d74f53"},
{file = "dirtyjson-1.0.8.tar.gz", hash = "sha256:90ca4a18f3ff30ce849d100dcf4a003953c79d3a2348ef056f1d9c22231a25fd"},
]
[[package]]
name = "distlib"
version = "0.3.8"
version = "0.3.9"
description = "Distribution utilities"
optional = false
python-versions = "*"
files = [
{file = "distlib-0.3.8-py2.py3-none-any.whl", hash = "sha256:034db59a0b96f8ca18035f36290806a9a6e6bd9d1ff91e45a7f172eb17e51784"},
{file = "distlib-0.3.8.tar.gz", hash = "sha256:1530ea13e350031b6312d8580ddb6b27a104275a31106523b8f123787f494f64"},
{file = "distlib-0.3.9-py2.py3-none-any.whl", hash = "sha256:47f8c22fd27c27e25a65601af709b38e4f0a45ea4fc2e710f65755fa8caaaf87"},
{file = "distlib-0.3.9.tar.gz", hash = "sha256:a60f20dea646b8a33f3e7772f74dc0b2d0772d2837ee1342a00645c81edf9403"},
]
[[package]]
@ -978,29 +953,30 @@ tabulate = "^0.9.0"
[package.source]
type = "git"
url = "ssh://git@github.com/DS4SD/docling-core.git"
reference = "5aa67df483fb82e01ebb8b86433459f86286403f"
resolved_reference = "5aa67df483fb82e01ebb8b86433459f86286403f"
url = "https://github.com/DS4SD/docling-core.git"
reference = "e42a1ddf36e53134aef92f0447cc3352a4e82e70"
resolved_reference = "e42a1ddf36e53134aef92f0447cc3352a4e82e70"
[[package]]
name = "docling-ibm-models"
version = "2.0.0"
description = "This package contains the AI models used by the Docling PDF conversion package"
optional = false
python-versions = "<4.0,>=3.10"
files = [
{file = "docling_ibm_models-2.0.0-py3-none-any.whl", hash = "sha256:ce40e70ef0dfd88bd80d4ee7c20b9d2f803b126f51ac171d9e38997942668dbc"},
{file = "docling_ibm_models-2.0.0.tar.gz", hash = "sha256:3db5e089ee138d2799acba21bfa8b6ac3e1cdbc2d50aeb608337934bdf24f69a"},
]
python-versions = "^3.10"
files = []
develop = false
[package.dependencies]
huggingface_hub = ">=0.23,<1"
jsonlines = ">=3.1.0,<4.0.0"
lxml = ">=4.9.1,<5.0.0"
mean_average_precision = ">=2021.4.26.0,<2022.0.0.0"
numpy = ">=1.24.4,<2.0.0"
opencv-python-headless = ">=4.6.0.66,<5.0.0.0"
Pillow = ">=10.0.0,<11.0.0"
jsonlines = "^3.1.0"
lxml = "^4.9.1"
mean_average_precision = "^2021.4.26.0"
numpy = [
{version = ">=2.1.0,<3.0.0", markers = "python_version >= \"3.13\""},
{version = ">=1.24.4,<2.0.0", markers = "python_version < \"3.13\""},
]
opencv-python-headless = "^4.6.0.66"
Pillow = "^10.0.0"
torch = [
{version = ">=2.2.2,<3.0.0", markers = "sys_platform != \"darwin\" or platform_machine != \"x86_64\""},
{version = ">=2.2.2,<2.3.0", markers = "sys_platform == \"darwin\" and platform_machine == \"x86_64\""},
@ -1009,42 +985,55 @@ torchvision = [
{version = ">=0,<1", markers = "sys_platform != \"darwin\" or platform_machine != \"x86_64\""},
{version = ">=0.17.2,<0.18.0", markers = "sys_platform == \"darwin\" and platform_machine == \"x86_64\""},
]
tqdm = ">=4.64.0,<5.0.0"
tqdm = "^4.64.0"
[package.source]
type = "git"
url = "https://github.com/DS4SD/docling-ibm-models.git"
reference = "1d2e2a2e6eb152c237f1383cdba20cf85db80b97"
resolved_reference = "1d2e2a2e6eb152c237f1383cdba20cf85db80b97"
[[package]]
name = "docling-parse"
version = "1.4.1"
version = "1.5.1"
description = "Simple package to extract text with coordinates from programmatic PDFs"
optional = false
python-versions = "<4.0,>=3.9"
files = [
{file = "docling_parse-1.4.1-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:bdc97c2ca978f6b6a3fd1333ca7bac9813a81d60ee7d20cd21963e7bbb983b8d"},
{file = "docling_parse-1.4.1-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:645b4188466e25b712f2cd9c3a4af822147c662d80d6eaa9dd35b24f82d8f120"},
{file = "docling_parse-1.4.1-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:36889eec1de02c485156bfda89c4c1ac02d23b1a30d7fd0da949b234171b97c5"},
{file = "docling_parse-1.4.1-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:176468841d5711efe6a4360cd03fa4a21cc1b974671e91a1f51341556c4cd048"},
{file = "docling_parse-1.4.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4071696520f5ba5f79217a2802948c9b0c87fe4e0e39d71e22a4d69c7e15bd9b"},
{file = "docling_parse-1.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:712ce5f1a1f241564090a5f40742a3f2bcd4a7a2b9bf7d871c2a517c6f399a00"},
{file = "docling_parse-1.4.1-cp310-cp310-win_amd64.whl", hash = "sha256:25418ad09321ee019fe8ebdc7ccb34d92e2af68e35decbf04c2fbb9d92863b16"},
{file = "docling_parse-1.4.1-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:87ad7adb9272f1374441a75e54aa034b1439dc6234d132c5fc15d0500d2729cd"},
{file = "docling_parse-1.4.1-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:a11853065c3a60d3b38a341fef323e53d6eb518314d7c9e708c9f85ce996801e"},
{file = "docling_parse-1.4.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:58d3f48a3185d8e77e47ede4cd5ff2c195e42f9fb1c0c21ec10d955b17b9774a"},
{file = "docling_parse-1.4.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:d800a7b9314a175564bdf2eb58d761419fe3260124542340a09052e871c3ee84"},
{file = "docling_parse-1.4.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b2fd0e54c7065d2f8e2edb47b00fa39f78fb35662e87ee808a61be3b893bd4c8"},
{file = "docling_parse-1.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:71506da01bcec785955d4329d1ac7a33f747a41283bfae911f0713042b27cfe5"},
{file = "docling_parse-1.4.1-cp311-cp311-win_amd64.whl", hash = "sha256:b8d90addcd3f37d4f3156244864186de2279e3c5b97242bc78aee0d30037df8f"},
{file = "docling_parse-1.4.1-cp312-cp312-macosx_13_0_arm64.whl", hash = "sha256:0ac471142ef9e12484ddf9d8ded75ed1905f1feab7981b55c7f56ca64e090551"},
{file = "docling_parse-1.4.1-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:f9fcd34cc8ef97879d65eee9590c0caa52ab99e240d5cec6bcf7d25e9f6c4812"},
{file = "docling_parse-1.4.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:2c4ebbbd9f7b6df3a45e17d0b2b8639c15e8ffc9d2bca520dd70ca73430642ea"},
{file = "docling_parse-1.4.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:00b5a850128ff7d113d528ad05cc45d6daa67c03a895997e2912ff858404d524"},
{file = "docling_parse-1.4.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5a4170590eef034a8b55cf1ba29d757961e08eb858e4a91426ee5e3930befa43"},
{file = "docling_parse-1.4.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f780d445f0edd78f7004bb7b230679dceed3f11d521ce25600b18f1df88edbe9"},
{file = "docling_parse-1.4.1-cp312-cp312-win_amd64.whl", hash = "sha256:f7a6363cc9aba84def07f61e54efb1c3ea0dda2e87bc72c88dea2688ba5c065e"},
{file = "docling_parse-1.4.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a6e427d92a43dc301168686b67ded6c9bb5fd713d4c96ba012bf24fae071a84b"},
{file = "docling_parse-1.4.1.tar.gz", hash = "sha256:7429bf8e171dfc0e6e11cdc7b8295d311b3f7fb0bb127b92c7f7a94fe0dfeb7b"},
{file = "docling_parse-1.5.1-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:f30ccdda94b41a13c6ba15e613815aa764b78d4c65fca06565f55e0749209942"},
{file = "docling_parse-1.5.1-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:82a2a6638947f424697d7857bf8caf9ff43bbe62557ce295f8e70db8c74fb1d6"},
{file = "docling_parse-1.5.1-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:15257757fa092625fe66188d34d3ec909d43745b0699a1bf18b2e2e3fbdf23aa"},
{file = "docling_parse-1.5.1-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:eaa896fcc1248c9f308d208b4a51d7374d5fa1224826443ce1d8705f489e97ef"},
{file = "docling_parse-1.5.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dcfd27ad928d49f6e2787c3afbf5067a5c4f7985c35076b861bbe7df824569f9"},
{file = "docling_parse-1.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e2125907b1ac170538da5433da0e8f800da8f031eebefeced52a8ec24df0bd5"},
{file = "docling_parse-1.5.1-cp310-cp310-win_amd64.whl", hash = "sha256:f453af5e016e5f2a277862cfdf8824bb8eadb8754c6a1f63c7a8436c4fb2d2bc"},
{file = "docling_parse-1.5.1-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:ab33b519e023d2b7d3cf03ce199480640b226d1f2f5c9e0f0878db921ba77837"},
{file = "docling_parse-1.5.1-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:4a185a9908a02b3596acb9f11952d96e5a42618f43e12b1e44bc311205284355"},
{file = "docling_parse-1.5.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:e89aa3c5c445127a9ca32a5b4c9ecc8b5d84b43223ebbdac2d40166e32f6ebbd"},
{file = "docling_parse-1.5.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:091583b1dbc481fc9527e9b10105a960e6a83bb75741e75ef73dfe508dcc666e"},
{file = "docling_parse-1.5.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:55fb2f69e2fdf266db5ecedca71fe829272f26e69e716c7397ad9e64f0a310dc"},
{file = "docling_parse-1.5.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b83a9666bf868d6cf81bc8753156e9e69e44aae86ac071e3830af6be5e950819"},
{file = "docling_parse-1.5.1-cp311-cp311-win_amd64.whl", hash = "sha256:b4e076161a657a153e281bd386942f8db962d378a6b126ef638566dcb1c5c5fc"},
{file = "docling_parse-1.5.1-cp312-cp312-macosx_13_0_arm64.whl", hash = "sha256:ff0baa6581446f719ceb98ca76c154b8802caf212b37267a8be7f82b0932e625"},
{file = "docling_parse-1.5.1-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:a748059d30b2e870e7c82cef5ef26c318739fc05d2b58639c3e385473da2d25a"},
{file = "docling_parse-1.5.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:4b5edfd749edfe91389cd664c3d2bd021744ca8c2db6b27ec129b0193cd67fb1"},
{file = "docling_parse-1.5.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:e6860ffcbfb04c11621c88f86670abe6fc4040da1f930d8b40b1d58411aa16b2"},
{file = "docling_parse-1.5.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:83e0bc50cad8ab0fffec5719c955fe55ef70fc7655cea71f8b63ded37ad91f3f"},
{file = "docling_parse-1.5.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3d63c3b5247d7a63484e5534ea2574f782c2cb958616fde0c962ec455cb5152"},
{file = "docling_parse-1.5.1-cp312-cp312-win_amd64.whl", hash = "sha256:aed1d5a7d693145da2473ca55408d94bb0555e2fd6a41c90c6d684d4f5dff52f"},
{file = "docling_parse-1.5.1-cp313-cp313-macosx_13_0_arm64.whl", hash = "sha256:784071e0a8f6cc12de9a365062b69813d903bff514093f316e92c7fa4768d6be"},
{file = "docling_parse-1.5.1-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:5f81d7154988baa38d9717be38e755ec409a8d577aad72c72b7bc4de2056be42"},
{file = "docling_parse-1.5.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:ba2053693790bba13b29c8a509aaaa046d603e74e7e46bef07ee7c61f2515a6a"},
{file = "docling_parse-1.5.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:bd561538f85a2d89ff1e905daad1f61abcb2b3d12db46038859ba793d214aaed"},
{file = "docling_parse-1.5.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:530d945f9bb64da7a3ba22fa2c107eaa2269811b0ff14ccea6b3be543f887c4b"},
{file = "docling_parse-1.5.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5c66991367d1744d69dc879b1419262116b1ba75a99a9e39beee40f58fd0dd7d"},
{file = "docling_parse-1.5.1-cp313-cp313-win_amd64.whl", hash = "sha256:53c4667eede313955d555848fd3d0f1d63613379151730c7027d2309728c590d"},
{file = "docling_parse-1.5.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:213dc9de5fdb45f687f84d2e3e910fe4838c20aa65e099119d23147fb12a98a9"},
{file = "docling_parse-1.5.1.tar.gz", hash = "sha256:2cd2bafb24834eeaea96be7fa2991fc444b3981bafb002e1332ad0f172f8cf32"},
]
[package.dependencies]
pywin32 = {version = ">=306,<307", markers = "sys_platform == \"win32\""}
pywin32 = {version = ">=305", markers = "sys_platform == \"win32\""}
tabulate = ">=0.9.0,<1.0.0"
[[package]]
@ -1447,92 +1436,6 @@ gitdb = ">=4.0.1,<5"
doc = ["sphinx (==4.3.2)", "sphinx-autodoc-typehints", "sphinx-rtd-theme", "sphinxcontrib-applehelp (>=1.0.2,<=1.0.4)", "sphinxcontrib-devhelp (==1.0.2)", "sphinxcontrib-htmlhelp (>=2.0.0,<=2.0.1)", "sphinxcontrib-qthelp (==1.0.3)", "sphinxcontrib-serializinghtml (==1.1.5)"]
test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit", "pytest (>=7.3.1)", "pytest-cov", "pytest-instafail", "pytest-mock", "pytest-sugar", "typing-extensions"]
[[package]]
name = "greenlet"
version = "3.1.1"
description = "Lightweight in-process concurrent programming"
optional = false
python-versions = ">=3.7"
files = [
{file = "greenlet-3.1.1-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:0bbae94a29c9e5c7e4a2b7f0aae5c17e8e90acbfd3bf6270eeba60c39fce3563"},
{file = "greenlet-3.1.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fde093fb93f35ca72a556cf72c92ea3ebfda3d79fc35bb19fbe685853869a83"},
{file = "greenlet-3.1.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:36b89d13c49216cadb828db8dfa6ce86bbbc476a82d3a6c397f0efae0525bdd0"},
{file = "greenlet-3.1.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:94b6150a85e1b33b40b1464a3f9988dcc5251d6ed06842abff82e42632fac120"},
{file = "greenlet-3.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93147c513fac16385d1036b7e5b102c7fbbdb163d556b791f0f11eada7ba65dc"},
{file = "greenlet-3.1.1-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:da7a9bff22ce038e19bf62c4dd1ec8391062878710ded0a845bcf47cc0200617"},
{file = "greenlet-3.1.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b2795058c23988728eec1f36a4e5e4ebad22f8320c85f3587b539b9ac84128d7"},
{file = "greenlet-3.1.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ed10eac5830befbdd0c32f83e8aa6288361597550ba669b04c48f0f9a2c843c6"},
{file = "greenlet-3.1.1-cp310-cp310-win_amd64.whl", hash = "sha256:77c386de38a60d1dfb8e55b8c1101d68c79dfdd25c7095d51fec2dd800892b80"},
{file = "greenlet-3.1.1-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:e4d333e558953648ca09d64f13e6d8f0523fa705f51cae3f03b5983489958c70"},
{file = "greenlet-3.1.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:09fc016b73c94e98e29af67ab7b9a879c307c6731a2c9da0db5a7d9b7edd1159"},
{file = "greenlet-3.1.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d5e975ca70269d66d17dd995dafc06f1b06e8cb1ec1e9ed54c1d1e4a7c4cf26e"},
{file = "greenlet-3.1.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3b2813dc3de8c1ee3f924e4d4227999285fd335d1bcc0d2be6dc3f1f6a318ec1"},
{file = "greenlet-3.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e347b3bfcf985a05e8c0b7d462ba6f15b1ee1c909e2dcad795e49e91b152c383"},
{file = "greenlet-3.1.1-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9e8f8c9cb53cdac7ba9793c276acd90168f416b9ce36799b9b885790f8ad6c0a"},
{file = "greenlet-3.1.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:62ee94988d6b4722ce0028644418d93a52429e977d742ca2ccbe1c4f4a792511"},
{file = "greenlet-3.1.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:1776fd7f989fc6b8d8c8cb8da1f6b82c5814957264d1f6cf818d475ec2bf6395"},
{file = "greenlet-3.1.1-cp311-cp311-win_amd64.whl", hash = "sha256:48ca08c771c268a768087b408658e216133aecd835c0ded47ce955381105ba39"},
{file = "greenlet-3.1.1-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:4afe7ea89de619adc868e087b4d2359282058479d7cfb94970adf4b55284574d"},
{file = "greenlet-3.1.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f406b22b7c9a9b4f8aa9d2ab13d6ae0ac3e85c9a809bd590ad53fed2bf70dc79"},
{file = "greenlet-3.1.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c3a701fe5a9695b238503ce5bbe8218e03c3bcccf7e204e455e7462d770268aa"},
{file = "greenlet-3.1.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2846930c65b47d70b9d178e89c7e1a69c95c1f68ea5aa0a58646b7a96df12441"},
{file = "greenlet-3.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99cfaa2110534e2cf3ba31a7abcac9d328d1d9f1b95beede58294a60348fba36"},
{file = "greenlet-3.1.1-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1443279c19fca463fc33e65ef2a935a5b09bb90f978beab37729e1c3c6c25fe9"},
{file = "greenlet-3.1.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b7cede291382a78f7bb5f04a529cb18e068dd29e0fb27376074b6d0317bf4dd0"},
{file = "greenlet-3.1.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:23f20bb60ae298d7d8656c6ec6db134bca379ecefadb0b19ce6f19d1f232a942"},
{file = "greenlet-3.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:7124e16b4c55d417577c2077be379514321916d5790fa287c9ed6f23bd2ffd01"},
{file = "greenlet-3.1.1-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:05175c27cb459dcfc05d026c4232f9de8913ed006d42713cb8a5137bd49375f1"},
{file = "greenlet-3.1.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:935e943ec47c4afab8965954bf49bfa639c05d4ccf9ef6e924188f762145c0ff"},
{file = "greenlet-3.1.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:667a9706c970cb552ede35aee17339a18e8f2a87a51fba2ed39ceeeb1004798a"},
{file = "greenlet-3.1.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b8a678974d1f3aa55f6cc34dc480169d58f2e6d8958895d68845fa4ab566509e"},
{file = "greenlet-3.1.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:efc0f674aa41b92da8c49e0346318c6075d734994c3c4e4430b1c3f853e498e4"},
{file = "greenlet-3.1.1-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0153404a4bb921f0ff1abeb5ce8a5131da56b953eda6e14b88dc6bbc04d2049e"},
{file = "greenlet-3.1.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:275f72decf9932639c1c6dd1013a1bc266438eb32710016a1c742df5da6e60a1"},
{file = "greenlet-3.1.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:c4aab7f6381f38a4b42f269057aee279ab0fc7bf2e929e3d4abfae97b682a12c"},
{file = "greenlet-3.1.1-cp313-cp313-win_amd64.whl", hash = "sha256:b42703b1cf69f2aa1df7d1030b9d77d3e584a70755674d60e710f0af570f3761"},
{file = "greenlet-3.1.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1695e76146579f8c06c1509c7ce4dfe0706f49c6831a817ac04eebb2fd02011"},
{file = "greenlet-3.1.1-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7876452af029456b3f3549b696bb36a06db7c90747740c5302f74a9e9fa14b13"},
{file = "greenlet-3.1.1-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4ead44c85f8ab905852d3de8d86f6f8baf77109f9da589cb4fa142bd3b57b475"},
{file = "greenlet-3.1.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8320f64b777d00dd7ccdade271eaf0cad6636343293a25074cc5566160e4de7b"},
{file = "greenlet-3.1.1-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6510bf84a6b643dabba74d3049ead221257603a253d0a9873f55f6a59a65f822"},
{file = "greenlet-3.1.1-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:04b013dc07c96f83134b1e99888e7a79979f1a247e2a9f59697fa14b5862ed01"},
{file = "greenlet-3.1.1-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:411f015496fec93c1c8cd4e5238da364e1da7a124bcb293f085bf2860c32c6f6"},
{file = "greenlet-3.1.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:47da355d8687fd65240c364c90a31569a133b7b60de111c255ef5b606f2ae291"},
{file = "greenlet-3.1.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:98884ecf2ffb7d7fe6bd517e8eb99d31ff7855a840fa6d0d63cd07c037f6a981"},
{file = "greenlet-3.1.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f1d4aeb8891338e60d1ab6127af1fe45def5259def8094b9c7e34690c8858803"},
{file = "greenlet-3.1.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:db32b5348615a04b82240cc67983cb315309e88d444a288934ee6ceaebcad6cc"},
{file = "greenlet-3.1.1-cp37-cp37m-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dcc62f31eae24de7f8dce72134c8651c58000d3b1868e01392baea7c32c247de"},
{file = "greenlet-3.1.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:1d3755bcb2e02de341c55b4fca7a745a24a9e7212ac953f6b3a48d117d7257aa"},
{file = "greenlet-3.1.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:b8da394b34370874b4572676f36acabac172602abf054cbc4ac910219f3340af"},
{file = "greenlet-3.1.1-cp37-cp37m-win32.whl", hash = "sha256:a0dfc6c143b519113354e780a50381508139b07d2177cb6ad6a08278ec655798"},
{file = "greenlet-3.1.1-cp37-cp37m-win_amd64.whl", hash = "sha256:54558ea205654b50c438029505def3834e80f0869a70fb15b871c29b4575ddef"},
{file = "greenlet-3.1.1-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:346bed03fe47414091be4ad44786d1bd8bef0c3fcad6ed3dee074a032ab408a9"},
{file = "greenlet-3.1.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dfc59d69fc48664bc693842bd57acfdd490acafda1ab52c7836e3fc75c90a111"},
{file = "greenlet-3.1.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d21e10da6ec19b457b82636209cbe2331ff4306b54d06fa04b7c138ba18c8a81"},
{file = "greenlet-3.1.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:37b9de5a96111fc15418819ab4c4432e4f3c2ede61e660b1e33971eba26ef9ba"},
{file = "greenlet-3.1.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6ef9ea3f137e5711f0dbe5f9263e8c009b7069d8a1acea822bd5e9dae0ae49c8"},
{file = "greenlet-3.1.1-cp38-cp38-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:85f3ff71e2e60bd4b4932a043fbbe0f499e263c628390b285cb599154a3b03b1"},
{file = "greenlet-3.1.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:95ffcf719966dd7c453f908e208e14cde192e09fde6c7186c8f1896ef778d8cd"},
{file = "greenlet-3.1.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:03a088b9de532cbfe2ba2034b2b85e82df37874681e8c470d6fb2f8c04d7e4b7"},
{file = "greenlet-3.1.1-cp38-cp38-win32.whl", hash = "sha256:8b8b36671f10ba80e159378df9c4f15c14098c4fd73a36b9ad715f057272fbef"},
{file = "greenlet-3.1.1-cp38-cp38-win_amd64.whl", hash = "sha256:7017b2be767b9d43cc31416aba48aab0d2309ee31b4dbf10a1d38fb7972bdf9d"},
{file = "greenlet-3.1.1-cp39-cp39-macosx_11_0_universal2.whl", hash = "sha256:396979749bd95f018296af156201d6211240e7a23090f50a8d5d18c370084dc3"},
{file = "greenlet-3.1.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca9d0ff5ad43e785350894d97e13633a66e2b50000e8a183a50a88d834752d42"},
{file = "greenlet-3.1.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f6ff3b14f2df4c41660a7dec01045a045653998784bf8cfcb5a525bdffffbc8f"},
{file = "greenlet-3.1.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:94ebba31df2aa506d7b14866fed00ac141a867e63143fe5bca82a8e503b36437"},
{file = "greenlet-3.1.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:73aaad12ac0ff500f62cebed98d8789198ea0e6f233421059fa68a5aa7220145"},
{file = "greenlet-3.1.1-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:63e4844797b975b9af3a3fb8f7866ff08775f5426925e1e0bbcfe7932059a12c"},
{file = "greenlet-3.1.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:7939aa3ca7d2a1593596e7ac6d59391ff30281ef280d8632fa03d81f7c5f955e"},
{file = "greenlet-3.1.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d0028e725ee18175c6e422797c407874da24381ce0690d6b9396c204c7f7276e"},
{file = "greenlet-3.1.1-cp39-cp39-win32.whl", hash = "sha256:5e06afd14cbaf9e00899fae69b24a32f2196c19de08fcb9f4779dd4f004e5e7c"},
{file = "greenlet-3.1.1-cp39-cp39-win_amd64.whl", hash = "sha256:3319aa75e0e0639bc15ff54ca327e8dc7a6fe404003496e3c6925cd3142e0e22"},
{file = "greenlet-3.1.1.tar.gz", hash = "sha256:4ce3ac6cdb6adf7946475d7ef31777c26d94bccc377e070a7986bd2d5c515467"},
]
[package.extras]
docs = ["Sphinx", "furo"]
test = ["objgraph", "psutil"]
[[package]]
name = "grpcio"
version = "1.66.2"
@ -1669,20 +1572,18 @@ zstd = ["zstandard (>=0.18.0)"]
[[package]]
name = "huggingface-hub"
version = "0.23.5"
version = "0.25.2"
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
optional = false
python-versions = ">=3.8.0"
files = [
{file = "huggingface_hub-0.23.5-py3-none-any.whl", hash = "sha256:d7a7d337615e11a45cc14a0ce5a605db6b038dc24af42866f731684825226e90"},
{file = "huggingface_hub-0.23.5.tar.gz", hash = "sha256:67a9caba79b71235be3752852ca27da86bd54311d2424ca8afdb8dda056edf98"},
{file = "huggingface_hub-0.25.2-py3-none-any.whl", hash = "sha256:1897caf88ce7f97fe0110603d8f66ac264e3ba6accdf30cd66cc0fed5282ad25"},
{file = "huggingface_hub-0.25.2.tar.gz", hash = "sha256:a1014ea111a5f40ccd23f7f7ba8ac46e20fa3b658ced1f86a00c75c06ec6423c"},
]
[package.dependencies]
aiohttp = {version = "*", optional = true, markers = "extra == \"inference\""}
filelock = "*"
fsspec = ">=2023.5.0"
minijinja = {version = ">=1.0", optional = true, markers = "extra == \"inference\""}
packaging = ">=20.9"
pyyaml = ">=5.1"
requests = "*"
@ -1690,17 +1591,17 @@ tqdm = ">=4.42.1"
typing-extensions = ">=3.7.4.3"
[package.extras]
all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.5.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
cli = ["InquirerPy (==0.3.4)"]
dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.5.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
hf-transfer = ["hf-transfer (>=0.1.4)"]
inference = ["aiohttp", "minijinja (>=1.0)"]
quality = ["mypy (==1.5.1)", "ruff (>=0.3.0)"]
quality = ["mypy (==1.5.1)", "ruff (>=0.5.0)"]
tensorflow = ["graphviz", "pydot", "tensorflow"]
tensorflow-testing = ["keras (<3.0)", "tensorflow"]
testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
torch = ["safetensors", "torch"]
testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
torch = ["safetensors[torch]", "torch"]
typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
[[package]]
@ -2424,13 +2325,13 @@ langchain-core = ">=0.2.38,<0.3.0"
[[package]]
name = "langsmith"
version = "0.1.132"
version = "0.1.133"
description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "langsmith-0.1.132-py3-none-any.whl", hash = "sha256:2320894203675c1c292b818cbecf68b69e47a9f7814d4e950237d1faaafd5dee"},
{file = "langsmith-0.1.132.tar.gz", hash = "sha256:007b8fac469138abdba89db931900a26c5d316640e27ff4660d28c92a766aae1"},
{file = "langsmith-0.1.133-py3-none-any.whl", hash = "sha256:82e837a6039c483beadbe19c2ba7ebafbd402d3e8105234f5ef334425cff7b45"},
{file = "langsmith-0.1.133.tar.gz", hash = "sha256:7bfd8bef166b9a64ee540a11bee4aa7bf43b1d9229f95b0fc19086454955185d"},
]
[package.dependencies]
@ -2508,86 +2409,6 @@ files = [
{file = "lazy_object_proxy-1.10.0-pp310.pp311.pp312.pp38.pp39-none-any.whl", hash = "sha256:80fa48bd89c8f2f456fc0765c11c23bf5af827febacd2f523ca5bc1893fcc09d"},
]
[[package]]
name = "llama-index-core"
version = "0.11.17"
description = "Interface between LLMs and your data"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "llama_index_core-0.11.17-py3-none-any.whl", hash = "sha256:d65565b54ea55b2db12f9a1cd5c250b770d7e43d3363137cff431a6116ef069c"},
{file = "llama_index_core-0.11.17.tar.gz", hash = "sha256:1143baf8d819e27555bdb142abdf2833d3d37731f270f46fa1e07fc4b97116ae"},
]
[package.dependencies]
aiohttp = ">=3.8.6,<4.0.0"
dataclasses-json = "*"
deprecated = ">=1.2.9.3"
dirtyjson = ">=1.0.8,<2.0.0"
fsspec = ">=2023.5.0"
httpx = "*"
nest-asyncio = ">=1.5.8,<2.0.0"
networkx = ">=3.0"
nltk = ">3.8.1"
numpy = "<2.0.0"
pillow = ">=9.0.0"
pydantic = ">=2.7.0,<3.0.0"
PyYAML = ">=6.0.1"
requests = ">=2.31.0"
SQLAlchemy = {version = ">=1.4.49", extras = ["asyncio"]}
tenacity = ">=8.2.0,<8.4.0 || >8.4.0,<9.0.0"
tiktoken = ">=0.3.3"
tqdm = ">=4.66.1,<5.0.0"
typing-extensions = ">=4.5.0"
typing-inspect = ">=0.8.0"
wrapt = "*"
[[package]]
name = "llama-index-embeddings-huggingface"
version = "0.3.1"
description = "llama-index embeddings huggingface integration"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "llama_index_embeddings_huggingface-0.3.1-py3-none-any.whl", hash = "sha256:71708240b1aec183c80f20d531b39a75d0cce774586e11bb0798f3ecb270749c"},
{file = "llama_index_embeddings_huggingface-0.3.1.tar.gz", hash = "sha256:7aef6324a19576e6b95bfe927c3bd4fc1c5725edce9f26b4e5d2eefa27c02fdb"},
]
[package.dependencies]
huggingface-hub = {version = ">=0.19.0", extras = ["inference"]}
llama-index-core = ">=0.11.0,<0.12.0"
sentence-transformers = ">=2.6.1"
[[package]]
name = "llama-index-llms-huggingface-api"
version = "0.2.0"
description = "llama-index llms huggingface api integration"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "llama_index_llms_huggingface_api-0.2.0-py3-none-any.whl", hash = "sha256:ed12bcf6986becee1dc5f7644ff22aa96070de3b463add22c3b6ceabc2bd2f43"},
{file = "llama_index_llms_huggingface_api-0.2.0.tar.gz", hash = "sha256:37c866071e2ebd668e4714ccaf69811c7be3891e07546a513b0aaf78259112fb"},
]
[package.dependencies]
huggingface-hub = ">=0.23.0,<0.24.0"
llama-index-core = ">=0.11.0,<0.12.0"
[[package]]
name = "llama-index-vector-stores-milvus"
version = "0.2.7"
description = "llama-index vector_stores milvus integration"
optional = false
python-versions = "<4.0,>=3.8.1"
files = [
{file = "llama_index_vector_stores_milvus-0.2.7-py3-none-any.whl", hash = "sha256:b3b309b15bf338ab2ebef494b93fc0f38fc1ef76c05d3bed290c2c17e131f41a"},
{file = "llama_index_vector_stores_milvus-0.2.7.tar.gz", hash = "sha256:d0074f62c5a1e64a3ac012dca5e2af63b5b973b4563f33bf4e7d52b505e563da"},
]
[package.dependencies]
llama-index-core = ">=0.11.0,<0.12.0"
pymilvus = ">=2.3.6,<3.0.0"
[[package]]
name = "lxml"
version = "4.9.4"
@ -2722,13 +2543,13 @@ testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
[[package]]
name = "markdown2"
version = "2.5.0"
version = "2.5.1"
description = "A fast and complete Python implementation of Markdown"
optional = false
python-versions = "<4,>=3.8"
files = [
{file = "markdown2-2.5.0-py2.py3-none-any.whl", hash = "sha256:300d4429b620ebc974ef512339a9e08bc080473f95135a91f33906e24e8280c1"},
{file = "markdown2-2.5.0.tar.gz", hash = "sha256:9bff02911f8b617b61eb269c4c1a5f9b2087d7ff051604f66a61b63cab30adc2"},
{file = "markdown2-2.5.1-py2.py3-none-any.whl", hash = "sha256:190ae60a4bd0425c60c863bede18a9f3d45b1cbf3fbc9f40b4fac336ff2c520b"},
{file = "markdown2-2.5.1.tar.gz", hash = "sha256:12fc04ea5a87f7bb4b65acf5bf3af1183b20838cc7d543b74c92ec7eea4bbc74"},
]
[package.extras]
@ -2969,23 +2790,6 @@ files = [
[package.dependencies]
tqdm = "*"
[[package]]
name = "minijinja"
version = "2.2.0"
description = "An experimental Python binding of the Rust MiniJinja template engine."
optional = false
python-versions = ">=3.8"
files = [
{file = "minijinja-2.2.0-cp38-abi3-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:e4154fcf72e81be01c2733b770e6cb3e584851cb2fa73c58e347b04967d3d7c0"},
{file = "minijinja-2.2.0-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4b05e0070c08b550fa9a09ff9c051f47424674332dd56cc54b997dd602887907"},
{file = "minijinja-2.2.0-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:360ea4a93fdf1fe327f3e70eed20ecb29f324ca28fae177de0605dcc29869300"},
{file = "minijinja-2.2.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c9cad5ccb021ef25b6a271158f4d6636474edb08cd1dd49355aac6b68a48aebb"},
{file = "minijinja-2.2.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:7a85c67c519b413fc4892854782927e1244a24cbbb3a3cb0ac5e57d9fdb1868c"},
{file = "minijinja-2.2.0-cp38-abi3-win32.whl", hash = "sha256:e431a2467dd6e1bcb7c511e9fbad012b02c6e5453acdd9fbd4c4af0d34a3d1c5"},
{file = "minijinja-2.2.0-cp38-abi3-win_amd64.whl", hash = "sha256:d4df7e4a09be4249c8243207fa89e6f4d22b853c2b565a99f48e478a30713822"},
{file = "minijinja-2.2.0.tar.gz", hash = "sha256:4411052c7a60f8d56468cc6d17d45d72be3d5e89e9578a04f8336cc56601523c"},
]
[[package]]
name = "more-itertools"
version = "10.5.0"
@ -3317,31 +3121,6 @@ files = [
[package.extras]
test = ["codecov (>=2.0.5)", "coverage (>=4.2)", "flake8 (>=3.0.4)", "pytest (>=4.5.0)", "pytest-cov (>=2.7.1)", "pytest-runner (>=5.1)", "pytest-virtualenv (>=1.7.0)", "virtualenv (>=15.0.3)"]
[[package]]
name = "nltk"
version = "3.9.1"
description = "Natural Language Toolkit"
optional = false
python-versions = ">=3.8"
files = [
{file = "nltk-3.9.1-py3-none-any.whl", hash = "sha256:4fa26829c5b00715afe3061398a8989dc643b92ce7dd93fb4585a70930d168a1"},
{file = "nltk-3.9.1.tar.gz", hash = "sha256:87d127bd3de4bd89a4f81265e5fa59cb1b199b27440175370f7417d2bc7ae868"},
]
[package.dependencies]
click = "*"
joblib = "*"
regex = ">=2021.8.3"
tqdm = "*"
[package.extras]
all = ["matplotlib", "numpy", "pyparsing", "python-crfsuite", "requests", "scikit-learn", "scipy", "twython"]
corenlp = ["requests"]
machine-learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
plot = ["matplotlib"]
tgrep = ["pyparsing"]
twitter = ["twython"]
[[package]]
name = "nodeenv"
version = "1.9.1"
@ -3408,6 +3187,68 @@ files = [
{file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
]
[[package]]
name = "numpy"
version = "2.1.2"
description = "Fundamental package for array computing in Python"
optional = false
python-versions = ">=3.10"
files = [
{file = "numpy-2.1.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:30d53720b726ec36a7f88dc873f0eec8447fbc93d93a8f079dfac2629598d6ee"},
{file = "numpy-2.1.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e8d3ca0a72dd8846eb6f7dfe8f19088060fcb76931ed592d29128e0219652884"},
{file = "numpy-2.1.2-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:fc44e3c68ff00fd991b59092a54350e6e4911152682b4782f68070985aa9e648"},
{file = "numpy-2.1.2-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:7c1c60328bd964b53f8b835df69ae8198659e2b9302ff9ebb7de4e5a5994db3d"},
{file = "numpy-2.1.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6cdb606a7478f9ad91c6283e238544451e3a95f30fb5467fbf715964341a8a86"},
{file = "numpy-2.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d666cb72687559689e9906197e3bec7b736764df6a2e58ee265e360663e9baf7"},
{file = "numpy-2.1.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c6eef7a2dbd0abfb0d9eaf78b73017dbfd0b54051102ff4e6a7b2980d5ac1a03"},
{file = "numpy-2.1.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:12edb90831ff481f7ef5f6bc6431a9d74dc0e5ff401559a71e5e4611d4f2d466"},
{file = "numpy-2.1.2-cp310-cp310-win32.whl", hash = "sha256:a65acfdb9c6ebb8368490dbafe83c03c7e277b37e6857f0caeadbbc56e12f4fb"},
{file = "numpy-2.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:860ec6e63e2c5c2ee5e9121808145c7bf86c96cca9ad396c0bd3e0f2798ccbe2"},
{file = "numpy-2.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b42a1a511c81cc78cbc4539675713bbcf9d9c3913386243ceff0e9429ca892fe"},
{file = "numpy-2.1.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:faa88bc527d0f097abdc2c663cddf37c05a1c2f113716601555249805cf573f1"},
{file = "numpy-2.1.2-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:c82af4b2ddd2ee72d1fc0c6695048d457e00b3582ccde72d8a1c991b808bb20f"},
{file = "numpy-2.1.2-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:13602b3174432a35b16c4cfb5de9a12d229727c3dd47a6ce35111f2ebdf66ff4"},
{file = "numpy-2.1.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1ebec5fd716c5a5b3d8dfcc439be82a8407b7b24b230d0ad28a81b61c2f4659a"},
{file = "numpy-2.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2b49c3c0804e8ecb05d59af8386ec2f74877f7ca8fd9c1e00be2672e4d399b1"},
{file = "numpy-2.1.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:2cbba4b30bf31ddbe97f1c7205ef976909a93a66bb1583e983adbd155ba72ac2"},
{file = "numpy-2.1.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8e00ea6fc82e8a804433d3e9cedaa1051a1422cb6e443011590c14d2dea59146"},
{file = "numpy-2.1.2-cp311-cp311-win32.whl", hash = "sha256:5006b13a06e0b38d561fab5ccc37581f23c9511879be7693bd33c7cd15ca227c"},
{file = "numpy-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:f1eb068ead09f4994dec71c24b2844f1e4e4e013b9629f812f292f04bd1510d9"},
{file = "numpy-2.1.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:d7bf0a4f9f15b32b5ba53147369e94296f5fffb783db5aacc1be15b4bf72f43b"},
{file = "numpy-2.1.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b1d0fcae4f0949f215d4632be684a539859b295e2d0cb14f78ec231915d644db"},
{file = "numpy-2.1.2-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:f751ed0a2f250541e19dfca9f1eafa31a392c71c832b6bb9e113b10d050cb0f1"},
{file = "numpy-2.1.2-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:bd33f82e95ba7ad632bc57837ee99dba3d7e006536200c4e9124089e1bf42426"},
{file = "numpy-2.1.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b8cde4f11f0a975d1fd59373b32e2f5a562ade7cde4f85b7137f3de8fbb29a0"},
{file = "numpy-2.1.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d95f286b8244b3649b477ac066c6906fbb2905f8ac19b170e2175d3d799f4df"},
{file = "numpy-2.1.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ab4754d432e3ac42d33a269c8567413bdb541689b02d93788af4131018cbf366"},
{file = "numpy-2.1.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e585c8ae871fd38ac50598f4763d73ec5497b0de9a0ab4ef5b69f01c6a046142"},
{file = "numpy-2.1.2-cp312-cp312-win32.whl", hash = "sha256:9c6c754df29ce6a89ed23afb25550d1c2d5fdb9901d9c67a16e0b16eaf7e2550"},
{file = "numpy-2.1.2-cp312-cp312-win_amd64.whl", hash = "sha256:456e3b11cb79ac9946c822a56346ec80275eaf2950314b249b512896c0d2505e"},
{file = "numpy-2.1.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:a84498e0d0a1174f2b3ed769b67b656aa5460c92c9554039e11f20a05650f00d"},
{file = "numpy-2.1.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:4d6ec0d4222e8ffdab1744da2560f07856421b367928026fb540e1945f2eeeaf"},
{file = "numpy-2.1.2-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:259ec80d54999cc34cd1eb8ded513cb053c3bf4829152a2e00de2371bd406f5e"},
{file = "numpy-2.1.2-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:675c741d4739af2dc20cd6c6a5c4b7355c728167845e3c6b0e824e4e5d36a6c3"},
{file = "numpy-2.1.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05b2d4e667895cc55e3ff2b56077e4c8a5604361fc21a042845ea3ad67465aa8"},
{file = "numpy-2.1.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:43cca367bf94a14aca50b89e9bc2061683116cfe864e56740e083392f533ce7a"},
{file = "numpy-2.1.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:76322dcdb16fccf2ac56f99048af32259dcc488d9b7e25b51e5eca5147a3fb98"},
{file = "numpy-2.1.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:32e16a03138cabe0cb28e1007ee82264296ac0983714094380b408097a418cfe"},
{file = "numpy-2.1.2-cp313-cp313-win32.whl", hash = "sha256:242b39d00e4944431a3cd2db2f5377e15b5785920421993770cddb89992c3f3a"},
{file = "numpy-2.1.2-cp313-cp313-win_amd64.whl", hash = "sha256:f2ded8d9b6f68cc26f8425eda5d3877b47343e68ca23d0d0846f4d312ecaa445"},
{file = "numpy-2.1.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:2ffef621c14ebb0188a8633348504a35c13680d6da93ab5cb86f4e54b7e922b5"},
{file = "numpy-2.1.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:ad369ed238b1959dfbade9018a740fb9392c5ac4f9b5173f420bd4f37ba1f7a0"},
{file = "numpy-2.1.2-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:d82075752f40c0ddf57e6e02673a17f6cb0f8eb3f587f63ca1eaab5594da5b17"},
{file = "numpy-2.1.2-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:1600068c262af1ca9580a527d43dc9d959b0b1d8e56f8a05d830eea39b7c8af6"},
{file = "numpy-2.1.2-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a26ae94658d3ba3781d5e103ac07a876b3e9b29db53f68ed7df432fd033358a8"},
{file = "numpy-2.1.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:13311c2db4c5f7609b462bc0f43d3c465424d25c626d95040f073e30f7570e35"},
{file = "numpy-2.1.2-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:2abbf905a0b568706391ec6fa15161fad0fb5d8b68d73c461b3c1bab6064dd62"},
{file = "numpy-2.1.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:ef444c57d664d35cac4e18c298c47d7b504c66b17c2ea91312e979fcfbdfb08a"},
{file = "numpy-2.1.2-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:bdd407c40483463898b84490770199d5714dcc9dd9b792f6c6caccc523c00952"},
{file = "numpy-2.1.2-pp310-pypy310_pp73-macosx_14_0_x86_64.whl", hash = "sha256:da65fb46d4cbb75cb417cddf6ba5e7582eb7bb0b47db4b99c9fe5787ce5d91f5"},
{file = "numpy-2.1.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1c193d0b0238638e6fc5f10f1b074a6993cb13b0b431f64079a509d63d3aa8b7"},
{file = "numpy-2.1.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a7d80b2e904faa63068ead63107189164ca443b42dd1930299e0d1cb041cec2e"},
{file = "numpy-2.1.2.tar.gz", hash = "sha256:13532a088217fa624c99b843eeb54640de23b3414b14aa66d023805eb731066c"},
]
[[package]]
name = "nvidia-cublas-cu12"
version = "12.1.3.1"
@ -4862,25 +4703,29 @@ files = [
[[package]]
name = "pywin32"
version = "306"
version = "307"
description = "Python for Window Extensions"
optional = false
python-versions = "*"
files = [
{file = "pywin32-306-cp310-cp310-win32.whl", hash = "sha256:06d3420a5155ba65f0b72f2699b5bacf3109f36acbe8923765c22938a69dfc8d"},
{file = "pywin32-306-cp310-cp310-win_amd64.whl", hash = "sha256:84f4471dbca1887ea3803d8848a1616429ac94a4a8d05f4bc9c5dcfd42ca99c8"},
{file = "pywin32-306-cp311-cp311-win32.whl", hash = "sha256:e65028133d15b64d2ed8f06dd9fbc268352478d4f9289e69c190ecd6818b6407"},
{file = "pywin32-306-cp311-cp311-win_amd64.whl", hash = "sha256:a7639f51c184c0272e93f244eb24dafca9b1855707d94c192d4a0b4c01e1100e"},
{file = "pywin32-306-cp311-cp311-win_arm64.whl", hash = "sha256:70dba0c913d19f942a2db25217d9a1b726c278f483a919f1abfed79c9cf64d3a"},
{file = "pywin32-306-cp312-cp312-win32.whl", hash = "sha256:383229d515657f4e3ed1343da8be101000562bf514591ff383ae940cad65458b"},
{file = "pywin32-306-cp312-cp312-win_amd64.whl", hash = "sha256:37257794c1ad39ee9be652da0462dc2e394c8159dfd913a8a4e8eb6fd346da0e"},
{file = "pywin32-306-cp312-cp312-win_arm64.whl", hash = "sha256:5821ec52f6d321aa59e2db7e0a35b997de60c201943557d108af9d4ae1ec7040"},
{file = "pywin32-306-cp37-cp37m-win32.whl", hash = "sha256:1c73ea9a0d2283d889001998059f5eaaba3b6238f767c9cf2833b13e6a685f65"},
{file = "pywin32-306-cp37-cp37m-win_amd64.whl", hash = "sha256:72c5f621542d7bdd4fdb716227be0dd3f8565c11b280be6315b06ace35487d36"},
{file = "pywin32-306-cp38-cp38-win32.whl", hash = "sha256:e4c092e2589b5cf0d365849e73e02c391c1349958c5ac3e9d5ccb9a28e017b3a"},
{file = "pywin32-306-cp38-cp38-win_amd64.whl", hash = "sha256:e8ac1ae3601bee6ca9f7cb4b5363bf1c0badb935ef243c4733ff9a393b1690c0"},
{file = "pywin32-306-cp39-cp39-win32.whl", hash = "sha256:e25fd5b485b55ac9c057f67d94bc203f3f6595078d1fb3b458c9c28b7153a802"},
{file = "pywin32-306-cp39-cp39-win_amd64.whl", hash = "sha256:39b61c15272833b5c329a2989999dcae836b1eed650252ab1b7bfbe1d59f30f4"},
{file = "pywin32-307-cp310-cp310-win32.whl", hash = "sha256:f8f25d893c1e1ce2d685ef6d0a481e87c6f510d0f3f117932781f412e0eba31b"},
{file = "pywin32-307-cp310-cp310-win_amd64.whl", hash = "sha256:36e650c5e5e6b29b5d317385b02d20803ddbac5d1031e1f88d20d76676dd103d"},
{file = "pywin32-307-cp310-cp310-win_arm64.whl", hash = "sha256:0c12d61e0274e0c62acee79e3e503c312426ddd0e8d4899c626cddc1cafe0ff4"},
{file = "pywin32-307-cp311-cp311-win32.whl", hash = "sha256:fec5d27cc893178fab299de911b8e4d12c5954e1baf83e8a664311e56a272b75"},
{file = "pywin32-307-cp311-cp311-win_amd64.whl", hash = "sha256:987a86971753ed7fdd52a7fb5747aba955b2c7fbbc3d8b76ec850358c1cc28c3"},
{file = "pywin32-307-cp311-cp311-win_arm64.whl", hash = "sha256:fd436897c186a2e693cd0437386ed79f989f4d13d6f353f8787ecbb0ae719398"},
{file = "pywin32-307-cp312-cp312-win32.whl", hash = "sha256:07649ec6b01712f36debf39fc94f3d696a46579e852f60157a729ac039df0815"},
{file = "pywin32-307-cp312-cp312-win_amd64.whl", hash = "sha256:00d047992bb5dcf79f8b9b7c81f72e0130f9fe4b22df613f755ab1cc021d8347"},
{file = "pywin32-307-cp312-cp312-win_arm64.whl", hash = "sha256:b53658acbfc6a8241d72cc09e9d1d666be4e6c99376bc59e26cdb6223c4554d2"},
{file = "pywin32-307-cp313-cp313-win32.whl", hash = "sha256:ea4d56e48dc1ab2aa0a5e3c0741ad6e926529510516db7a3b6981a1ae74405e5"},
{file = "pywin32-307-cp313-cp313-win_amd64.whl", hash = "sha256:576d09813eaf4c8168d0bfd66fb7cb3b15a61041cf41598c2db4a4583bf832d2"},
{file = "pywin32-307-cp313-cp313-win_arm64.whl", hash = "sha256:b30c9bdbffda6a260beb2919f918daced23d32c79109412c2085cbc513338a0a"},
{file = "pywin32-307-cp37-cp37m-win32.whl", hash = "sha256:5101472f5180c647d4525a0ed289ec723a26231550dbfd369ec19d5faf60e511"},
{file = "pywin32-307-cp37-cp37m-win_amd64.whl", hash = "sha256:05de55a7c110478dc4b202230e98af5e0720855360d2b31a44bb4e296d795fba"},
{file = "pywin32-307-cp38-cp38-win32.whl", hash = "sha256:13d059fb7f10792542082f5731d5d3d9645320fc38814759313e5ee97c3fac01"},
{file = "pywin32-307-cp38-cp38-win_amd64.whl", hash = "sha256:7e0b2f93769d450a98ac7a31a087e07b126b6d571e8b4386a5762eb85325270b"},
{file = "pywin32-307-cp39-cp39-win32.whl", hash = "sha256:55ee87f2f8c294e72ad9d4261ca423022310a6e79fb314a8ca76ab3f493854c6"},
{file = "pywin32-307-cp39-cp39-win_amd64.whl", hash = "sha256:e9d5202922e74985b037c9ef46778335c102b74b95cec70f629453dbe7235d87"},
]
[[package]]
@ -5990,93 +5835,6 @@ files = [
{file = "soupsieve-2.6.tar.gz", hash = "sha256:e2e68417777af359ec65daac1057404a3c8a5455bb8abc36f1a9866ab1a51abb"},
]
[[package]]
name = "sqlalchemy"
version = "2.0.35"
description = "Database Abstraction Library"
optional = false
python-versions = ">=3.7"
files = [
{file = "SQLAlchemy-2.0.35-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:67219632be22f14750f0d1c70e62f204ba69d28f62fd6432ba05ab295853de9b"},
{file = "SQLAlchemy-2.0.35-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4668bd8faf7e5b71c0319407b608f278f279668f358857dbfd10ef1954ac9f90"},
{file = "SQLAlchemy-2.0.35-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb8bea573863762bbf45d1e13f87c2d2fd32cee2dbd50d050f83f87429c9e1ea"},
{file = "SQLAlchemy-2.0.35-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f552023710d4b93d8fb29a91fadf97de89c5926c6bd758897875435f2a939f33"},
{file = "SQLAlchemy-2.0.35-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:016b2e665f778f13d3c438651dd4de244214b527a275e0acf1d44c05bc6026a9"},
{file = "SQLAlchemy-2.0.35-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:7befc148de64b6060937231cbff8d01ccf0bfd75aa26383ffdf8d82b12ec04ff"},
{file = "SQLAlchemy-2.0.35-cp310-cp310-win32.whl", hash = "sha256:22b83aed390e3099584b839b93f80a0f4a95ee7f48270c97c90acd40ee646f0b"},
{file = "SQLAlchemy-2.0.35-cp310-cp310-win_amd64.whl", hash = "sha256:a29762cd3d116585278ffb2e5b8cc311fb095ea278b96feef28d0b423154858e"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e21f66748ab725ade40fa7af8ec8b5019c68ab00b929f6643e1b1af461eddb60"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8a6219108a15fc6d24de499d0d515c7235c617b2540d97116b663dade1a54d62"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:042622a5306c23b972192283f4e22372da3b8ddf5f7aac1cc5d9c9b222ab3ff6"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:627dee0c280eea91aed87b20a1f849e9ae2fe719d52cbf847c0e0ea34464b3f7"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:4fdcd72a789c1c31ed242fd8c1bcd9ea186a98ee8e5408a50e610edfef980d71"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:89b64cd8898a3a6f642db4eb7b26d1b28a497d4022eccd7717ca066823e9fb01"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-win32.whl", hash = "sha256:6a93c5a0dfe8d34951e8a6f499a9479ffb9258123551fa007fc708ae2ac2bc5e"},
{file = "SQLAlchemy-2.0.35-cp311-cp311-win_amd64.whl", hash = "sha256:c68fe3fcde03920c46697585620135b4ecfdfc1ed23e75cc2c2ae9f8502c10b8"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:eb60b026d8ad0c97917cb81d3662d0b39b8ff1335e3fabb24984c6acd0c900a2"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6921ee01caf375363be5e9ae70d08ce7ca9d7e0e8983183080211a062d299468"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8cdf1a0dbe5ced887a9b127da4ffd7354e9c1a3b9bb330dce84df6b70ccb3a8d"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93a71c8601e823236ac0e5d087e4f397874a421017b3318fd92c0b14acf2b6db"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e04b622bb8a88f10e439084486f2f6349bf4d50605ac3e445869c7ea5cf0fa8c"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:1b56961e2d31389aaadf4906d453859f35302b4eb818d34a26fab72596076bb8"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-win32.whl", hash = "sha256:0f9f3f9a3763b9c4deb8c5d09c4cc52ffe49f9876af41cc1b2ad0138878453cf"},
{file = "SQLAlchemy-2.0.35-cp312-cp312-win_amd64.whl", hash = "sha256:25b0f63e7fcc2a6290cb5f7f5b4fc4047843504983a28856ce9b35d8f7de03cc"},
{file = "SQLAlchemy-2.0.35-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:f021d334f2ca692523aaf7bbf7592ceff70c8594fad853416a81d66b35e3abf9"},
{file = "SQLAlchemy-2.0.35-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05c3f58cf91683102f2f0265c0db3bd3892e9eedabe059720492dbaa4f922da1"},
{file = "SQLAlchemy-2.0.35-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:032d979ce77a6c2432653322ba4cbeabf5a6837f704d16fa38b5a05d8e21fa00"},
{file = "SQLAlchemy-2.0.35-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:2e795c2f7d7249b75bb5f479b432a51b59041580d20599d4e112b5f2046437a3"},
{file = "SQLAlchemy-2.0.35-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:cc32b2990fc34380ec2f6195f33a76b6cdaa9eecf09f0c9404b74fc120aef36f"},
{file = "SQLAlchemy-2.0.35-cp37-cp37m-win32.whl", hash = "sha256:9509c4123491d0e63fb5e16199e09f8e262066e58903e84615c301dde8fa2e87"},
{file = "SQLAlchemy-2.0.35-cp37-cp37m-win_amd64.whl", hash = "sha256:3655af10ebcc0f1e4e06c5900bb33e080d6a1fa4228f502121f28a3b1753cde5"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4c31943b61ed8fdd63dfd12ccc919f2bf95eefca133767db6fbbd15da62078ec"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a62dd5d7cc8626a3634208df458c5fe4f21200d96a74d122c83bc2015b333bc1"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0630774b0977804fba4b6bbea6852ab56c14965a2b0c7fc7282c5f7d90a1ae72"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d625eddf7efeba2abfd9c014a22c0f6b3796e0ffb48f5d5ab106568ef01ff5a"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:ada603db10bb865bbe591939de854faf2c60f43c9b763e90f653224138f910d9"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:c41411e192f8d3ea39ea70e0fae48762cd11a2244e03751a98bd3c0ca9a4e936"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-win32.whl", hash = "sha256:d299797d75cd747e7797b1b41817111406b8b10a4f88b6e8fe5b5e59598b43b0"},
{file = "SQLAlchemy-2.0.35-cp38-cp38-win_amd64.whl", hash = "sha256:0375a141e1c0878103eb3d719eb6d5aa444b490c96f3fedab8471c7f6ffe70ee"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ccae5de2a0140d8be6838c331604f91d6fafd0735dbdcee1ac78fc8fbaba76b4"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2a275a806f73e849e1c309ac11108ea1a14cd7058577aba962cd7190e27c9e3c"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:732e026240cdd1c1b2e3ac515c7a23820430ed94292ce33806a95869c46bd139"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:890da8cd1941fa3dab28c5bac3b9da8502e7e366f895b3b8e500896f12f94d11"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:c0d8326269dbf944b9201911b0d9f3dc524d64779a07518199a58384c3d37a44"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:b76d63495b0508ab9fc23f8152bac63205d2a704cd009a2b0722f4c8e0cba8e0"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-win32.whl", hash = "sha256:69683e02e8a9de37f17985905a5eca18ad651bf592314b4d3d799029797d0eb3"},
{file = "SQLAlchemy-2.0.35-cp39-cp39-win_amd64.whl", hash = "sha256:aee110e4ef3c528f3abbc3c2018c121e708938adeeff9006428dd7c8555e9b3f"},
{file = "SQLAlchemy-2.0.35-py3-none-any.whl", hash = "sha256:2ab3f0336c0387662ce6221ad30ab3a5e6499aab01b9790879b6578fd9b8faa1"},
{file = "sqlalchemy-2.0.35.tar.gz", hash = "sha256:e11d7ea4d24f0a262bccf9a7cd6284c976c5369dac21db237cff59586045ab9f"},
]
[package.dependencies]
greenlet = {version = "!=0.4.17", optional = true, markers = "python_version < \"3.13\" and (platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\") or extra == \"asyncio\""}
typing-extensions = ">=4.6.0"
[package.extras]
aiomysql = ["aiomysql (>=0.2.0)", "greenlet (!=0.4.17)"]
aioodbc = ["aioodbc", "greenlet (!=0.4.17)"]
aiosqlite = ["aiosqlite", "greenlet (!=0.4.17)", "typing_extensions (!=3.10.0.1)"]
asyncio = ["greenlet (!=0.4.17)"]
asyncmy = ["asyncmy (>=0.2.3,!=0.2.4,!=0.2.6)", "greenlet (!=0.4.17)"]
mariadb-connector = ["mariadb (>=1.0.1,!=1.1.2,!=1.1.5)"]
mssql = ["pyodbc"]
mssql-pymssql = ["pymssql"]
mssql-pyodbc = ["pyodbc"]
mypy = ["mypy (>=0.910)"]
mysql = ["mysqlclient (>=1.4.0)"]
mysql-connector = ["mysql-connector-python"]
oracle = ["cx_oracle (>=8)"]
oracle-oracledb = ["oracledb (>=1.0.1)"]
postgresql = ["psycopg2 (>=2.7)"]
postgresql-asyncpg = ["asyncpg", "greenlet (!=0.4.17)"]
postgresql-pg8000 = ["pg8000 (>=1.29.1)"]
postgresql-psycopg = ["psycopg (>=3.0.7)"]
postgresql-psycopg2binary = ["psycopg2-binary"]
postgresql-psycopg2cffi = ["psycopg2cffi"]
postgresql-psycopgbinary = ["psycopg[binary] (>=3.0.7)"]
pymysql = ["pymysql"]
sqlcipher = ["sqlcipher3_binary"]
[[package]]
name = "stack-data"
version = "0.6.3"
@ -6210,53 +5968,6 @@ test = ["cmapfile", "czifile", "dask", "defusedxml", "fsspec", "imagecodecs", "l
xml = ["defusedxml", "lxml"]
zarr = ["fsspec", "zarr"]
[[package]]
name = "tiktoken"
version = "0.8.0"
description = "tiktoken is a fast BPE tokeniser for use with OpenAI's models"
optional = false
python-versions = ">=3.9"
files = [
{file = "tiktoken-0.8.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b07e33283463089c81ef1467180e3e00ab00d46c2c4bbcef0acab5f771d6695e"},
{file = "tiktoken-0.8.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9269348cb650726f44dd3bbb3f9110ac19a8dcc8f54949ad3ef652ca22a38e21"},
{file = "tiktoken-0.8.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:25e13f37bc4ef2d012731e93e0fef21dc3b7aea5bb9009618de9a4026844e560"},
{file = "tiktoken-0.8.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f13d13c981511331eac0d01a59b5df7c0d4060a8be1e378672822213da51e0a2"},
{file = "tiktoken-0.8.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:6b2ddbc79a22621ce8b1166afa9f9a888a664a579350dc7c09346a3b5de837d9"},
{file = "tiktoken-0.8.0-cp310-cp310-win_amd64.whl", hash = "sha256:d8c2d0e5ba6453a290b86cd65fc51fedf247e1ba170191715b049dac1f628005"},
{file = "tiktoken-0.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d622d8011e6d6f239297efa42a2657043aaed06c4f68833550cac9e9bc723ef1"},
{file = "tiktoken-0.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2efaf6199717b4485031b4d6edb94075e4d79177a172f38dd934d911b588d54a"},
{file = "tiktoken-0.8.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5637e425ce1fc49cf716d88df3092048359a4b3bbb7da762840426e937ada06d"},
{file = "tiktoken-0.8.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9fb0e352d1dbe15aba082883058b3cce9e48d33101bdaac1eccf66424feb5b47"},
{file = "tiktoken-0.8.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:56edfefe896c8f10aba372ab5706b9e3558e78db39dd497c940b47bf228bc419"},
{file = "tiktoken-0.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:326624128590def898775b722ccc327e90b073714227175ea8febbc920ac0a99"},
{file = "tiktoken-0.8.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:881839cfeae051b3628d9823b2e56b5cc93a9e2efb435f4cf15f17dc45f21586"},
{file = "tiktoken-0.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:fe9399bdc3f29d428f16a2f86c3c8ec20be3eac5f53693ce4980371c3245729b"},
{file = "tiktoken-0.8.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9a58deb7075d5b69237a3ff4bb51a726670419db6ea62bdcd8bd80c78497d7ab"},
{file = "tiktoken-0.8.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2908c0d043a7d03ebd80347266b0e58440bdef5564f84f4d29fb235b5df3b04"},
{file = "tiktoken-0.8.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:294440d21a2a51e12d4238e68a5972095534fe9878be57d905c476017bff99fc"},
{file = "tiktoken-0.8.0-cp312-cp312-win_amd64.whl", hash = "sha256:d8f3192733ac4d77977432947d563d7e1b310b96497acd3c196c9bddb36ed9db"},
{file = "tiktoken-0.8.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:02be1666096aff7da6cbd7cdaa8e7917bfed3467cd64b38b1f112e96d3b06a24"},
{file = "tiktoken-0.8.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:c94ff53c5c74b535b2cbf431d907fc13c678bbd009ee633a2aca269a04389f9a"},
{file = "tiktoken-0.8.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6b231f5e8982c245ee3065cd84a4712d64692348bc609d84467c57b4b72dcbc5"},
{file = "tiktoken-0.8.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4177faa809bd55f699e88c96d9bb4635d22e3f59d635ba6fd9ffedf7150b9953"},
{file = "tiktoken-0.8.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:5376b6f8dc4753cd81ead935c5f518fa0fbe7e133d9e25f648d8c4dabdd4bad7"},
{file = "tiktoken-0.8.0-cp313-cp313-win_amd64.whl", hash = "sha256:18228d624807d66c87acd8f25fc135665617cab220671eb65b50f5d70fa51f69"},
{file = "tiktoken-0.8.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7e17807445f0cf1f25771c9d86496bd8b5c376f7419912519699f3cc4dc5c12e"},
{file = "tiktoken-0.8.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:886f80bd339578bbdba6ed6d0567a0d5c6cfe198d9e587ba6c447654c65b8edc"},
{file = "tiktoken-0.8.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6adc8323016d7758d6de7313527f755b0fc6c72985b7d9291be5d96d73ecd1e1"},
{file = "tiktoken-0.8.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b591fb2b30d6a72121a80be24ec7a0e9eb51c5500ddc7e4c2496516dd5e3816b"},
{file = "tiktoken-0.8.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:845287b9798e476b4d762c3ebda5102be87ca26e5d2c9854002825d60cdb815d"},
{file = "tiktoken-0.8.0-cp39-cp39-win_amd64.whl", hash = "sha256:1473cfe584252dc3fa62adceb5b1c763c1874e04511b197da4e6de51d6ce5a02"},
{file = "tiktoken-0.8.0.tar.gz", hash = "sha256:9ccbb2740f24542534369c5635cfd9b2b3c2490754a78ac8831d99f89f94eeb2"},
]
[package.dependencies]
regex = ">=2022.1.18"
requests = ">=2.26.0"
[package.extras]
blobfile = ["blobfile (>=2)"]
[[package]]
name = "tokenize-rt"
version = "6.0.0"
@ -6270,111 +5981,111 @@ files = [
[[package]]
name = "tokenizers"
version = "0.20.0"
version = "0.20.1"
description = ""
optional = false
python-versions = ">=3.7"
files = [
{file = "tokenizers-0.20.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:6cff5c5e37c41bc5faa519d6f3df0679e4b37da54ea1f42121719c5e2b4905c0"},
{file = "tokenizers-0.20.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:62a56bf75c27443432456f4ca5ca055befa95e25be8a28141cc495cac8ae4d6d"},
{file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68cc7de6a63f09c4a86909c2597b995aa66e19df852a23aea894929c74369929"},
{file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:053c37ecee482cc958fdee53af3c6534286a86f5d35aac476f7c246830e53ae5"},
{file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3d7074aaabc151a6363fa03db5493fc95b423b2a1874456783989e96d541c7b6"},
{file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a11435780f2acd89e8fefe5e81cecf01776f6edb9b3ac95bcb76baee76b30b90"},
{file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9a81cd2712973b007d84268d45fc3f6f90a79c31dfe7f1925e6732f8d2959987"},
{file = "tokenizers-0.20.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7dfd796ab9d909f76fb93080e1c7c8309f196ecb316eb130718cd5e34231c69"},
{file = "tokenizers-0.20.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:8029ad2aa8cb00605c9374566034c1cc1b15130713e0eb5afcef6cface8255c9"},
{file = "tokenizers-0.20.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ca4d54260ebe97d59dfa9a30baa20d0c4dd9137d99a8801700055c561145c24e"},
{file = "tokenizers-0.20.0-cp310-none-win32.whl", hash = "sha256:95ee16b57cec11b86a7940174ec5197d506439b0f415ab3859f254b1dffe9df0"},
{file = "tokenizers-0.20.0-cp310-none-win_amd64.whl", hash = "sha256:0a61a11e93eeadbf02aea082ffc75241c4198e0608bbbac4f65a9026851dcf37"},
{file = "tokenizers-0.20.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:6636b798b3c4d6c9b1af1a918bd07c867808e5a21c64324e95318a237e6366c3"},
{file = "tokenizers-0.20.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:5ec603e42eaf499ffd58b9258162add948717cf21372458132f14e13a6bc7172"},
{file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cce124264903a8ea6f8f48e1cc7669e5ef638c18bd4ab0a88769d5f92debdf7f"},
{file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:07bbeba0231cf8de07aa6b9e33e9779ff103d47042eeeb859a8c432e3292fb98"},
{file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:06c0ca8397b35d38b83a44a9c6929790c1692957d88541df061cb34d82ebbf08"},
{file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ca6557ac3b83d912dfbb1f70ab56bd4b0594043916688e906ede09f42e192401"},
{file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a5ad94c9e80ac6098328bee2e3264dbced4c6faa34429994d473f795ec58ef4"},
{file = "tokenizers-0.20.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b5c7f906ee6bec30a9dc20268a8b80f3b9584de1c9f051671cb057dc6ce28f6"},
{file = "tokenizers-0.20.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:31e087e9ee1b8f075b002bfee257e858dc695f955b43903e1bb4aa9f170e37fe"},
{file = "tokenizers-0.20.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:c3124fb6f3346cb3d8d775375d3b429bf4dcfc24f739822702009d20a4297990"},
{file = "tokenizers-0.20.0-cp311-none-win32.whl", hash = "sha256:a4bb8b40ba9eefa621fdcabf04a74aa6038ae3be0c614c6458bd91a4697a452f"},
{file = "tokenizers-0.20.0-cp311-none-win_amd64.whl", hash = "sha256:2b709d371f1fe60a28ef0c5c67815952d455ca7f34dbe7197eaaed3cc54b658e"},
{file = "tokenizers-0.20.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:15c81a17d0d66f4987c6ca16f4bea7ec253b8c7ed1bb00fdc5d038b1bb56e714"},
{file = "tokenizers-0.20.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6a531cdf1fb6dc41c984c785a3b299cb0586de0b35683842a3afbb1e5207f910"},
{file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:06caabeb4587f8404e0cd9d40f458e9cba3e815c8155a38e579a74ff3e2a4301"},
{file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8768f964f23f5b9f50546c0369c75ab3262de926983888bbe8b98be05392a79c"},
{file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:626403860152c816f97b649fd279bd622c3d417678c93b4b1a8909b6380b69a8"},
{file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9c1b88fa9e5ff062326f4bf82681da5a96fca7104d921a6bd7b1e6fcf224af26"},
{file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3d7e559436a07dc547f22ce1101f26d8b2fad387e28ec8e7e1e3b11695d681d8"},
{file = "tokenizers-0.20.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e48afb75e50449848964e4a67b0da01261dd3aa8df8daecf10db8fd7f5b076eb"},
{file = "tokenizers-0.20.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:baf5d0e1ff44710a95eefc196dd87666ffc609fd447c5e5b68272a7c3d342a1d"},
{file = "tokenizers-0.20.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e5e56df0e8ed23ba60ae3848c3f069a0710c4b197218fe4f89e27eba38510768"},
{file = "tokenizers-0.20.0-cp312-none-win32.whl", hash = "sha256:ec53e5ecc142a82432f9c6c677dbbe5a2bfee92b8abf409a9ecb0d425ee0ce75"},
{file = "tokenizers-0.20.0-cp312-none-win_amd64.whl", hash = "sha256:f18661ece72e39c0dfaa174d6223248a15b457dbd4b0fc07809b8e6d3ca1a234"},
{file = "tokenizers-0.20.0-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:f7065b1084d8d1a03dc89d9aad69bcbc8415d4bc123c367063eb32958cd85054"},
{file = "tokenizers-0.20.0-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:e5d4069e4714e3f7ba0a4d3d44f9d84a432cd4e4aa85c3d7dd1f51440f12e4a1"},
{file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:799b808529e54b7e1a36350bda2aeb470e8390e484d3e98c10395cee61d4e3c6"},
{file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7f9baa027cc8a281ad5f7725a93c204d7a46986f88edbe8ef7357f40a23fb9c7"},
{file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:010ec7f3f7a96adc4c2a34a3ada41fa14b4b936b5628b4ff7b33791258646c6b"},
{file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:98d88f06155335b14fd78e32ee28ca5b2eb30fced4614e06eb14ae5f7fba24ed"},
{file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e13eb000ef540c2280758d1b9cfa5fe424b0424ae4458f440e6340a4f18b2638"},
{file = "tokenizers-0.20.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fab3cf066ff426f7e6d70435dc28a9ff01b2747be83810e397cba106f39430b0"},
{file = "tokenizers-0.20.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:39fa3761b30a89368f322e5daf4130dce8495b79ad831f370449cdacfb0c0d37"},
{file = "tokenizers-0.20.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c8da0fba4d179ddf2607821575998df3c294aa59aa8df5a6646dc64bc7352bce"},
{file = "tokenizers-0.20.0-cp37-none-win32.whl", hash = "sha256:fada996d6da8cf213f6e3c91c12297ad4f6cdf7a85c2fadcd05ec32fa6846fcd"},
{file = "tokenizers-0.20.0-cp37-none-win_amd64.whl", hash = "sha256:7d29aad702279e0760c265fcae832e89349078e3418dd329732d4503259fd6bd"},
{file = "tokenizers-0.20.0-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:099c68207f3ef0227ecb6f80ab98ea74de559f7b124adc7b17778af0250ee90a"},
{file = "tokenizers-0.20.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:68012d8a8cddb2eab3880870d7e2086cb359c7f7a2b03f5795044f5abff4e850"},
{file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9253bdd209c6aee168deca7d0e780581bf303e0058f268f9bb06859379de19b6"},
{file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8f868600ddbcb0545905ed075eb7218a0756bf6c09dae7528ea2f8436ebd2c93"},
{file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9a9643d9c8c5f99b6aba43fd10034f77cc6c22c31f496d2f0ee183047d948fa0"},
{file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c375c6a889aeab44734028bc65cc070acf93ccb0f9368be42b67a98e1063d3f6"},
{file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e359f852328e254f070bbd09a19a568421d23388f04aad9f2fb7da7704c7228d"},
{file = "tokenizers-0.20.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d98b01a309d4387f3b1c1dd68a8b8136af50376cf146c1b7e8d8ead217a5be4b"},
{file = "tokenizers-0.20.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:459f7537119554c2899067dec1ac74a00d02beef6558f4ee2e99513bf6d568af"},
{file = "tokenizers-0.20.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:392b87ec89452628c045c9f2a88bc2a827f4c79e7d84bc3b72752b74c2581f70"},
{file = "tokenizers-0.20.0-cp38-none-win32.whl", hash = "sha256:55a393f893d2ed4dd95a1553c2e42d4d4086878266f437b03590d3f81984c4fe"},
{file = "tokenizers-0.20.0-cp38-none-win_amd64.whl", hash = "sha256:30ffe33c5c2f2aab8e9a3340d0110dd9f7ace7eec7362e20a697802306bd8068"},
{file = "tokenizers-0.20.0-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:aa2d4a6fed2a7e3f860c7fc9d48764bb30f2649d83915d66150d6340e06742b8"},
{file = "tokenizers-0.20.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b5ef0f814084a897e9071fc4a868595f018c5c92889197bdc4bf19018769b148"},
{file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc1e1b791e8c3bf4c4f265f180dadaff1c957bf27129e16fdd5e5d43c2d3762c"},
{file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2b69e55e481459c07885263743a0d3c18d52db19bae8226a19bcca4aaa213fff"},
{file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4806b4d82e27a2512bc23057b2986bc8b85824914286975b84d8105ff40d03d9"},
{file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9859e9ef13adf5a473ccab39d31bff9c550606ae3c784bf772b40f615742a24f"},
{file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ef703efedf4c20488a8eb17637b55973745b27997ff87bad88ed499b397d1144"},
{file = "tokenizers-0.20.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6eec0061bab94b1841ab87d10831fdf1b48ebaed60e6d66d66dbe1d873f92bf5"},
{file = "tokenizers-0.20.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:980f3d0d7e73f845b69087f29a63c11c7eb924c4ad6b358da60f3db4cf24bdb4"},
{file = "tokenizers-0.20.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:7c157550a2f3851b29d7fdc9dc059fcf81ff0c0fc49a1e5173a89d533ed043fa"},
{file = "tokenizers-0.20.0-cp39-none-win32.whl", hash = "sha256:8a3d2f4d08608ec4f9895ec25b4b36a97f05812543190a5f2c3cd19e8f041e5a"},
{file = "tokenizers-0.20.0-cp39-none-win_amd64.whl", hash = "sha256:d90188d12afd0c75e537f9a1d92f9c7375650188ee4f48fdc76f9e38afbd2251"},
{file = "tokenizers-0.20.0-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:d68e15f1815357b059ec266062340c343ea7f98f7f330602df81ffa3474b6122"},
{file = "tokenizers-0.20.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:23f9ecec637b9bc80da5f703808d29ed5329e56b5aa8d791d1088014f48afadc"},
{file = "tokenizers-0.20.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f830b318ee599e3d0665b3e325f85bc75ee2d2ca6285f52e439dc22b64691580"},
{file = "tokenizers-0.20.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b3dc750def789cb1de1b5a37657919545e1d9ffa667658b3fa9cb7862407a1b8"},
{file = "tokenizers-0.20.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e26e6c755ae884c2ea6135cd215bdd0fccafe4ee62405014b8c3cd19954e3ab9"},
{file = "tokenizers-0.20.0-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:a1158c7174f427182e08baa2a8ded2940f2b4a3e94969a85cc9cfd16004cbcea"},
{file = "tokenizers-0.20.0-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:6324826287a3fc198898d3dcf758fe4a8479e42d6039f4c59e2cedd3cf92f64e"},
{file = "tokenizers-0.20.0-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:7d8653149405bb0c16feaf9cfee327fdb6aaef9dc2998349fec686f35e81c4e2"},
{file = "tokenizers-0.20.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b8a2dc1e402a155e97309287ca085c80eb1b7fab8ae91527d3b729181639fa51"},
{file = "tokenizers-0.20.0-pp37-pypy37_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:07bef67b20aa6e5f7868c42c7c5eae4d24f856274a464ae62e47a0f2cccec3da"},
{file = "tokenizers-0.20.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da06e397182ff53789c506c7833220c192952c57e1581a53f503d8d953e2d67e"},
{file = "tokenizers-0.20.0-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:302f7e11a14814028b7fc88c45a41f1bbe9b5b35fd76d6869558d1d1809baa43"},
{file = "tokenizers-0.20.0-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:055ec46e807b875589dfbe3d9259f9a6ee43394fb553b03b3d1e9541662dbf25"},
{file = "tokenizers-0.20.0-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e3144b8acebfa6ae062e8f45f7ed52e4b50fb6c62f93afc8871b525ab9fdcab3"},
{file = "tokenizers-0.20.0-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:b52aa3fd14b2a07588c00a19f66511cff5cca8f7266ca3edcdd17f3512ad159f"},
{file = "tokenizers-0.20.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2b8cf52779ffc5d4d63a0170fbeb512372bad0dd014ce92bbb9149756c831124"},
{file = "tokenizers-0.20.0-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:983a45dd11a876124378dae71d6d9761822199b68a4c73f32873d8cdaf326a5b"},
{file = "tokenizers-0.20.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df6b819c9a19831ebec581e71a7686a54ab45d90faf3842269a10c11d746de0c"},
{file = "tokenizers-0.20.0-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e738cfd80795fcafcef89c5731c84b05638a4ab3f412f97d5ed7765466576eb1"},
{file = "tokenizers-0.20.0-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:c8842c7be2fadb9c9edcee233b1b7fe7ade406c99b0973f07439985c1c1d0683"},
{file = "tokenizers-0.20.0-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e47a82355511c373a4a430c4909dc1e518e00031207b1fec536c49127388886b"},
{file = "tokenizers-0.20.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:9afbf359004551179a5db19424180c81276682773cff2c5d002f6eaaffe17230"},
{file = "tokenizers-0.20.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a07eaa8799a92e6af6f472c21a75bf71575de2af3c0284120b7a09297c0de2f3"},
{file = "tokenizers-0.20.0-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0994b2e5fc53a301071806bc4303e4bc3bdc3f490e92a21338146a36746b0872"},
{file = "tokenizers-0.20.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b6466e0355b603d10e3cc3d282d350b646341b601e50969464a54939f9848d0"},
{file = "tokenizers-0.20.0-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:1e86594c2a433cb1ea09cfbe596454448c566e57ee8905bd557e489d93e89986"},
{file = "tokenizers-0.20.0-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:3e14cdef1efa96ecead6ea64a891828432c3ebba128bdc0596e3059fea104ef3"},
{file = "tokenizers-0.20.0.tar.gz", hash = "sha256:39d7acc43f564c274085cafcd1dae9d36f332456de1a31970296a6b8da4eac8d"},
{file = "tokenizers-0.20.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:439261da7c0a5c88bda97acb284d49fbdaf67e9d3b623c0bfd107512d22787a9"},
{file = "tokenizers-0.20.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:03dae629d99068b1ea5416d50de0fea13008f04129cc79af77a2a6392792d93c"},
{file = "tokenizers-0.20.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b61f561f329ffe4b28367798b89d60c4abf3f815d37413b6352bc6412a359867"},
{file = "tokenizers-0.20.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ec870fce1ee5248a10be69f7a8408a234d6f2109f8ea827b4f7ecdbf08c9fd15"},
{file = "tokenizers-0.20.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d388d1ea8b7447da784e32e3b86a75cce55887e3b22b31c19d0b186b1c677800"},
{file = "tokenizers-0.20.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:299c85c1d21135bc01542237979bf25c32efa0d66595dd0069ae259b97fb2dbe"},
{file = "tokenizers-0.20.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e96f6c14c9752bb82145636b614d5a78e9cde95edfbe0a85dad0dd5ddd6ec95c"},
{file = "tokenizers-0.20.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc9e95ad49c932b80abfbfeaf63b155761e695ad9f8a58c52a47d962d76e310f"},
{file = "tokenizers-0.20.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:f22dee205329a636148c325921c73cf3e412e87d31f4d9c3153b302a0200057b"},
{file = "tokenizers-0.20.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a2ffd9a8895575ac636d44500c66dffaef133823b6b25067604fa73bbc5ec09d"},
{file = "tokenizers-0.20.1-cp310-none-win32.whl", hash = "sha256:2847843c53f445e0f19ea842a4e48b89dd0db4e62ba6e1e47a2749d6ec11f50d"},
{file = "tokenizers-0.20.1-cp310-none-win_amd64.whl", hash = "sha256:f9aa93eacd865f2798b9e62f7ce4533cfff4f5fbd50c02926a78e81c74e432cd"},
{file = "tokenizers-0.20.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:4a717dcb08f2dabbf27ae4b6b20cbbb2ad7ed78ce05a829fae100ff4b3c7ff15"},
{file = "tokenizers-0.20.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3f84dad1ff1863c648d80628b1b55353d16303431283e4efbb6ab1af56a75832"},
{file = "tokenizers-0.20.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:929c8f3afa16a5130a81ab5079c589226273ec618949cce79b46d96e59a84f61"},
{file = "tokenizers-0.20.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d10766473954397e2d370f215ebed1cc46dcf6fd3906a2a116aa1d6219bfedc3"},
{file = "tokenizers-0.20.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9300fac73ddc7e4b0330acbdda4efaabf74929a4a61e119a32a181f534a11b47"},
{file = "tokenizers-0.20.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0ecaf7b0e39caeb1aa6dd6e0975c405716c82c1312b55ac4f716ef563a906969"},
{file = "tokenizers-0.20.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5170be9ec942f3d1d317817ced8d749b3e1202670865e4fd465e35d8c259de83"},
{file = "tokenizers-0.20.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ef3f1ae08fa9aea5891cbd69df29913e11d3841798e0bfb1ff78b78e4e7ea0a4"},
{file = "tokenizers-0.20.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ee86d4095d3542d73579e953c2e5e07d9321af2ffea6ecc097d16d538a2dea16"},
{file = "tokenizers-0.20.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:86dcd08da163912e17b27bbaba5efdc71b4fbffb841530fdb74c5707f3c49216"},
{file = "tokenizers-0.20.1-cp311-none-win32.whl", hash = "sha256:9af2dc4ee97d037bc6b05fa4429ddc87532c706316c5e11ce2f0596dfcfa77af"},
{file = "tokenizers-0.20.1-cp311-none-win_amd64.whl", hash = "sha256:899152a78b095559c287b4c6d0099469573bb2055347bb8154db106651296f39"},
{file = "tokenizers-0.20.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:407ab666b38e02228fa785e81f7cf79ef929f104bcccf68a64525a54a93ceac9"},
{file = "tokenizers-0.20.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2f13a2d16032ebc8bd812eb8099b035ac65887d8f0c207261472803b9633cf3e"},
{file = "tokenizers-0.20.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e98eee4dca22849fbb56a80acaa899eec5b72055d79637dd6aa15d5e4b8628c9"},
{file = "tokenizers-0.20.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:47c1bcdd61e61136087459cb9e0b069ff23b5568b008265e5cbc927eae3387ce"},
{file = "tokenizers-0.20.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:128c1110e950534426e2274837fc06b118ab5f2fa61c3436e60e0aada0ccfd67"},
{file = "tokenizers-0.20.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e2e2d47a819d2954f2c1cd0ad51bb58ffac6f53a872d5d82d65d79bf76b9896d"},
{file = "tokenizers-0.20.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bdd67a0e3503a9a7cf8bc5a4a49cdde5fa5bada09a51e4c7e1c73900297539bd"},
{file = "tokenizers-0.20.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:689b93d2e26d04da337ac407acec8b5d081d8d135e3e5066a88edd5bdb5aff89"},
{file = "tokenizers-0.20.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0c6a796ddcd9a19ad13cf146997cd5895a421fe6aec8fd970d69f9117bddb45c"},
{file = "tokenizers-0.20.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:3ea919687aa7001a8ff1ba36ac64f165c4e89035f57998fa6cedcfd877be619d"},
{file = "tokenizers-0.20.1-cp312-none-win32.whl", hash = "sha256:6d3ac5c1f48358ffe20086bf065e843c0d0a9fce0d7f0f45d5f2f9fba3609ca5"},
{file = "tokenizers-0.20.1-cp312-none-win_amd64.whl", hash = "sha256:b0874481aea54a178f2bccc45aa2d0c99cd3f79143a0948af6a9a21dcc49173b"},
{file = "tokenizers-0.20.1-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:96af92e833bd44760fb17f23f402e07a66339c1dcbe17d79a9b55bb0cc4f038e"},
{file = "tokenizers-0.20.1-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:65f34e5b731a262dfa562820818533c38ce32a45864437f3d9c82f26c139ca7f"},
{file = "tokenizers-0.20.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:17f98fccb5c12ab1ce1f471731a9cd86df5d4bd2cf2880c5a66b229802d96145"},
{file = "tokenizers-0.20.1-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:b8c0fc3542cf9370bf92c932eb71bdeb33d2d4aeeb4126d9fd567b60bd04cb30"},
{file = "tokenizers-0.20.1-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4b39356df4575d37f9b187bb623aab5abb7b62c8cb702867a1768002f814800c"},
{file = "tokenizers-0.20.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bfdad27b0e50544f6b838895a373db6114b85112ba5c0cefadffa78d6daae563"},
{file = "tokenizers-0.20.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:094663dd0e85ee2e573126918747bdb40044a848fde388efb5b09d57bc74c680"},
{file = "tokenizers-0.20.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:14e4cf033a2aa207d7ac790e91adca598b679999710a632c4a494aab0fc3a1b2"},
{file = "tokenizers-0.20.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:9310951c92c9fb91660de0c19a923c432f110dbfad1a2d429fbc44fa956bf64f"},
{file = "tokenizers-0.20.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:05e41e302c315bd2ed86c02e917bf03a6cf7d2f652c9cee1a0eb0d0f1ca0d32c"},
{file = "tokenizers-0.20.1-cp37-none-win32.whl", hash = "sha256:212231ab7dfcdc879baf4892ca87c726259fa7c887e1688e3f3cead384d8c305"},
{file = "tokenizers-0.20.1-cp37-none-win_amd64.whl", hash = "sha256:896195eb9dfdc85c8c052e29947169c1fcbe75a254c4b5792cdbd451587bce85"},
{file = "tokenizers-0.20.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:741fb22788482d09d68e73ece1495cfc6d9b29a06c37b3df90564a9cfa688e6d"},
{file = "tokenizers-0.20.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:10be14ebd8082086a342d969e17fc2d6edc856c59dbdbddd25f158fa40eaf043"},
{file = "tokenizers-0.20.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:514cf279b22fa1ae0bc08e143458c74ad3b56cd078b319464959685a35c53d5e"},
{file = "tokenizers-0.20.1-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a647c5b7cb896d6430cf3e01b4e9a2d77f719c84cefcef825d404830c2071da2"},
{file = "tokenizers-0.20.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7cdf379219e1e1dd432091058dab325a2e6235ebb23e0aec8d0508567c90cd01"},
{file = "tokenizers-0.20.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ba72260449e16c4c2f6f3252823b059fbf2d31b32617e582003f2b18b415c39"},
{file = "tokenizers-0.20.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:910b96ed87316e4277b23c7bcaf667ce849c7cc379a453fa179e7e09290eeb25"},
{file = "tokenizers-0.20.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e53975a6694428a0586534cc1354b2408d4e010a3103117f617cbb550299797c"},
{file = "tokenizers-0.20.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:07c4b7be58da142b0730cc4e5fd66bb7bf6f57f4986ddda73833cd39efef8a01"},
{file = "tokenizers-0.20.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b605c540753e62199bf15cf69c333e934077ef2350262af2ccada46026f83d1c"},
{file = "tokenizers-0.20.1-cp38-none-win32.whl", hash = "sha256:88b3bc76ab4db1ab95ead623d49c95205411e26302cf9f74203e762ac7e85685"},
{file = "tokenizers-0.20.1-cp38-none-win_amd64.whl", hash = "sha256:d412a74cf5b3f68a90c615611a5aa4478bb303d1c65961d22db45001df68afcb"},
{file = "tokenizers-0.20.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:a25dcb2f41a0a6aac31999e6c96a75e9152fa0127af8ece46c2f784f23b8197a"},
{file = "tokenizers-0.20.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a12c3cebb8c92e9c35a23ab10d3852aee522f385c28d0b4fe48c0b7527d59762"},
{file = "tokenizers-0.20.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:02e18da58cf115b7c40de973609c35bde95856012ba42a41ee919c77935af251"},
{file = "tokenizers-0.20.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f326a1ac51ae909b9760e34671c26cd0dfe15662f447302a9d5bb2d872bab8ab"},
{file = "tokenizers-0.20.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0b4872647ea6f25224e2833b044b0b19084e39400e8ead3cfe751238b0802140"},
{file = "tokenizers-0.20.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ce6238a3311bb8e4c15b12600927d35c267b92a52c881ef5717a900ca14793f7"},
{file = "tokenizers-0.20.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:57b7a8880b208866508b06ce365dc631e7a2472a3faa24daa430d046fb56c885"},
{file = "tokenizers-0.20.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a908c69c2897a68f412aa05ba38bfa87a02980df70f5a72fa8490479308b1f2d"},
{file = "tokenizers-0.20.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:da1001aa46f4490099c82e2facc4fbc06a6a32bf7de3918ba798010954b775e0"},
{file = "tokenizers-0.20.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:42c097390e2f0ed0a5c5d569e6669dd4e9fff7b31c6a5ce6e9c66a61687197de"},
{file = "tokenizers-0.20.1-cp39-none-win32.whl", hash = "sha256:3d4d218573a3d8b121a1f8c801029d70444ffb6d8f129d4cca1c7b672ee4a24c"},
{file = "tokenizers-0.20.1-cp39-none-win_amd64.whl", hash = "sha256:37d1e6f616c84fceefa7c6484a01df05caf1e207669121c66213cb5b2911d653"},
{file = "tokenizers-0.20.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:48689da7a395df41114f516208d6550e3e905e1239cc5ad386686d9358e9cef0"},
{file = "tokenizers-0.20.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:712f90ea33f9bd2586b4a90d697c26d56d0a22fd3c91104c5858c4b5b6489a79"},
{file = "tokenizers-0.20.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:359eceb6a620c965988fc559cebc0a98db26713758ec4df43fb76d41486a8ed5"},
{file = "tokenizers-0.20.1-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0d3caf244ce89d24c87545aafc3448be15870096e796c703a0d68547187192e1"},
{file = "tokenizers-0.20.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:03b03cf8b9a32254b1bf8a305fb95c6daf1baae0c1f93b27f2b08c9759f41dee"},
{file = "tokenizers-0.20.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:218e5a3561561ea0f0ef1559c6d95b825308dbec23fb55b70b92589e7ff2e1e8"},
{file = "tokenizers-0.20.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f40df5e0294a95131cc5f0e0eb91fe86d88837abfbee46b9b3610b09860195a7"},
{file = "tokenizers-0.20.1-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:08aaa0d72bb65058e8c4b0455f61b840b156c557e2aca57627056624c3a93976"},
{file = "tokenizers-0.20.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:998700177b45f70afeb206ad22c08d9e5f3a80639dae1032bf41e8cbc4dada4b"},
{file = "tokenizers-0.20.1-pp37-pypy37_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62f7fbd3c2c38b179556d879edae442b45f68312019c3a6013e56c3947a4e648"},
{file = "tokenizers-0.20.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:31e87fca4f6bbf5cc67481b562147fe932f73d5602734de7dd18a8f2eee9c6dd"},
{file = "tokenizers-0.20.1-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:956f21d359ae29dd51ca5726d2c9a44ffafa041c623f5aa33749da87cfa809b9"},
{file = "tokenizers-0.20.1-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:1fbbaf17a393c78d8aedb6a334097c91cb4119a9ced4764ab8cfdc8d254dc9f9"},
{file = "tokenizers-0.20.1-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:ebe63e31f9c1a970c53866d814e35ec2ec26fda03097c486f82f3891cee60830"},
{file = "tokenizers-0.20.1-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:81970b80b8ac126910295f8aab2d7ef962009ea39e0d86d304769493f69aaa1e"},
{file = "tokenizers-0.20.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:130e35e76f9337ed6c31be386e75d4925ea807055acf18ca1a9b0eec03d8fe23"},
{file = "tokenizers-0.20.1-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cd28a8614f5c82a54ab2463554e84ad79526c5184cf4573bbac2efbbbcead457"},
{file = "tokenizers-0.20.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9041ee665d0fa7f5c4ccf0f81f5e6b7087f797f85b143c094126fc2611fec9d0"},
{file = "tokenizers-0.20.1-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:62eb9daea2a2c06bcd8113a5824af8ef8ee7405d3a71123ba4d52c79bb3d9f1a"},
{file = "tokenizers-0.20.1-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f861889707b54a9ab1204030b65fd6c22bdd4a95205deec7994dc22a8baa2ea4"},
{file = "tokenizers-0.20.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:89d5c337d74ea6e5e7dc8af124cf177be843bbb9ca6e58c01f75ea103c12c8a9"},
{file = "tokenizers-0.20.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:0b7f515c83397e73292accdbbbedc62264e070bae9682f06061e2ddce67cacaf"},
{file = "tokenizers-0.20.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e0305fc1ec6b1e5052d30d9c1d5c807081a7bd0cae46a33d03117082e91908c"},
{file = "tokenizers-0.20.1-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5dc611e6ac0fa00a41de19c3bf6391a05ea201d2d22b757d63f5491ec0e67faa"},
{file = "tokenizers-0.20.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c5ffe0d7f7bfcfa3b2585776ecf11da2e01c317027c8573c78ebcb8985279e23"},
{file = "tokenizers-0.20.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e7edb8ec12c100d5458d15b1e47c0eb30ad606a05641f19af7563bc3d1608c14"},
{file = "tokenizers-0.20.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:de291633fb9303555793cc544d4a86e858da529b7d0b752bcaf721ae1d74b2c9"},
{file = "tokenizers-0.20.1.tar.gz", hash = "sha256:84edcc7cdeeee45ceedb65d518fffb77aec69311c9c8e30f77ad84da3025f002"},
]
[package.dependencies]
@ -7388,4 +7099,4 @@ tesserocr = ["tesserocr"]
[metadata]
lock-version = "2.0"
python-versions = "^3.10"
content-hash = "24bcab2ca88de60d345409465bfa61b740b5168ccb60ad1a9027763c569c71d7"
content-hash = "19a3c34b2ad4ba98576d6a0453103f95cdc0e729cbc619417b92f565713183a1"

14
pyproject.toml
View File

@ -37,9 +37,10 @@ torchvision = [
######################
python = "^3.10"
pydantic = "^2.0.0"
docling-core = {git = "ssh://git@github.com/DS4SD/docling-core.git", rev = "5aa67df483fb82e01ebb8b86433459f86286403f"}
docling-ibm-models = "^2.0.0"
deepsearch-glm = {git = "ssh://git@github.com/DS4SD/deepsearch-glm.git", rev = "880c6eb50ecdc2c7ec5f3039b257b51cac6199ca"}
docling-core = {git = "https://github.com/DS4SD/docling-core.git", rev = "e42a1ddf36e53134aef92f0447cc3352a4e82e70"}
docling-ibm-models = {git = "https://github.com/DS4SD/docling-ibm-models.git", rev = "1d2e2a2e6eb152c237f1383cdba20cf85db80b97"}
deepsearch-glm = {git = "https://github.com/DS4SD/deepsearch-glm.git", rev = "a5bcc9fd90d50cc1899da2f878ae8259269ab9bf"}
docling-parse = "^1.5.1"
filetype = "^1.2.0"
pypdfium2 = "^4.30.0"
@ -48,7 +49,6 @@ huggingface_hub = ">=0.23,<1"
requests = "^2.32.3"
easyocr = "^1.7"
tesserocr = { version = "^2.7.1", optional = true }
docling-parse = "^1.4.1"
certifi = ">=2024.7.4"
rtree = "^1.3.0"
scipy = "^1.14.1"
@ -80,9 +80,9 @@ nbqa = "^1.9.0"
[tool.poetry.group.examples.dependencies]
datasets = "^2.21.0"
python-dotenv = "^1.0.1"
llama-index-embeddings-huggingface = "^0.3.1"
llama-index-llms-huggingface-api = "^0.2.0"
llama-index-vector-stores-milvus = "^0.2.1"
# llama-index-embeddings-huggingface = { version = "^0.3.1", markers = 'python_version < "3.13"' }
# llama-index-llms-huggingface-api = { version = "^0.2.0", markers = 'python_version < "3.13"' }
# llama-index-vector-stores-milvus = { version = "^0.2.1", markers = 'python_version < "3.13"' }
langchain-huggingface = "^0.0.3"
langchain-milvus = "^0.1.4"
langchain-text-splitters = "^0.2.4"

BIN
tests/data/2305.03393v1-pg9-img.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 301 KiB

1
tests/data/groundtruth/docling_v2/2203.01017v2.doctags.txt
View File

@ -37,7 +37,6 @@
<list_item><location><page_2><loc_10><loc_25><loc_47><loc_29></location>· We present SynthTabNet a synthetically generated dataset, with various appearance styles and complexity.</list_item>
<list_item><location><page_2><loc_10><loc_19><loc_47><loc_24></location>· An augmented dataset based on PubTabNet [37], FinTabNet [36], and TableBank [17] with generated ground-truth for reproducibility.</list_item>
<text><location><page_2><loc_8><loc_12><loc_47><loc_18></location>The paper is structured as follows. In Sec. 2, we give a brief overview of the current state-of-the-art. In Sec. 3, we describe the datasets on which we train. In Sec. 4, we introduce the TableFormer model-architecture and describe</text>
<footnote><location><page_2><loc_10><loc_10><loc_30><loc_11></location>$^{1}$https://github.com/IBM/SynthTabNet</footnote>
<text><location><page_2><loc_50><loc_86><loc_89><loc_91></location>its results & performance in Sec. 5. As a conclusion, we describe how this new model-architecture can be re-purposed for other tasks in the computer-vision community.</text>
<section_header><location><page_2><loc_50><loc_83><loc_81><loc_85></location>2. Previous work and State of the Art</section_header>
<text><location><page_2><loc_50><loc_58><loc_89><loc_82></location>Identifying the structure of a table has been an outstanding problem in the document-parsing community, that motivates many organised public challenges [6, 4, 14]. The difficulty of the problem can be attributed to a number of factors. First, there is a large variety in the shapes and sizes of tables. Such large variety requires a flexible method. This is especially true for complex column- and row headers, which can be extremely intricate and demanding. A second factor of complexity is the lack of data with regard to table-structure. Until the publication of PubTabNet [37], there were no large datasets (i.e. > 100 K tables) that provided structure information. This happens primarily due to the fact that tables are notoriously time-consuming to annotate by hand. However, this has definitely changed in recent years with the deliverance of PubTabNet [37], FinTabNet [36], TableBank [17] etc.</text>

2
tests/data/groundtruth/docling_v2/2203.01017v2.md
View File

@ -53,8 +53,6 @@ To meet the design criteria listed above, we developed a new model called TableF
The paper is structured as follows. In Sec. 2, we give a brief overview of the current state-of-the-art. In Sec. 3, we describe the datasets on which we train. In Sec. 4, we introduce the TableFormer model-architecture and describe
$^{1}$https://github.com/IBM/SynthTabNet
its results & performance in Sec. 5. As a conclusion, we describe how this new model-architecture can be re-purposed for other tasks in the computer-vision community.
## 2. Previous work and State of the Art

3
tests/data/groundtruth/docling_v2/2206.01062.doctags.txt
View File

@ -39,7 +39,6 @@
<list_item><location><page_2><loc_10><loc_20><loc_48><loc_22></location>(2) Large Layout Variability : We include diverse and complex layouts from a large variety of public sources.</list_item>
<list_item><location><page_2><loc_10><loc_15><loc_48><loc_19></location>(3) Detailed Label Set : We define 11 class labels to distinguish layout features in high detail. PubLayNet provides 5 labels; DocBank provides 13, although not a superset of ours.</list_item>
<list_item><location><page_2><loc_11><loc_13><loc_48><loc_15></location>(4) Redundant Annotations : A fraction of the pages in the DocLayNet data set carry more than one human annotation.</list_item>
<footnote><location><page_2><loc_9><loc_10><loc_35><loc_11></location>$^{1}$https://developer.ibm.com/exchanges/data/all/doclaynet</footnote>
<text><location><page_2><loc_56><loc_87><loc_91><loc_89></location>This enables experimentation with annotation uncertainty and quality control analysis.</text>
<list_item><location><page_2><loc_54><loc_80><loc_91><loc_86></location>(5) Pre-defined Train-, Test- & Validation-set : Like DocBank, we provide fixed train-, test- & validation-sets to ensure proportional representation of the class-labels. Further, we prevent leakage of unique layouts across sets, which has a large effect on model accuracy scores.</list_item>
<text><location><page_2><loc_52><loc_72><loc_91><loc_79></location>All aspects outlined above are detailed in Section 3. In Section 4, we will elaborate on how we designed and executed this large-scale human annotation campaign. We will also share key insights and lessons learned that might prove helpful for other parties planning to set up annotation campaigns.</text>
@ -58,7 +57,6 @@
<text><location><page_3><loc_9><loc_36><loc_48><loc_53></location>The pages in DocLayNet can be grouped into six distinct categories, namely Financial Reports , Manuals , Scientific Articles , Laws & Regulations , Patents and Government Tenders . Each document category was sourced from various repositories. For example, Financial Reports contain both free-style format annual reports 2 which expose company-specific, artistic layouts as well as the more formal SEC filings. The two largest categories ( Financial Reports and Manuals ) contain a large amount of free-style layouts in order to obtain maximum variability. In the other four categories, we boosted the variability by mixing documents from independent providers, such as different government websites or publishers. In Figure 2, we show the document categories contained in DocLayNet with their respective sizes.</text>
<text><location><page_3><loc_9><loc_23><loc_48><loc_36></location>We did not control the document selection with regard to language. The vast majority of documents contained in DocLayNet (close to 95%) are published in English language. However, DocLayNet also contains a number of documents in other languages such as German (2.5%), French (1.0%) and Japanese (1.0%). While the document language has negligible impact on the performance of computer vision methods such as object detection and segmentation models, it might prove challenging for layout analysis methods which exploit textual features.</text>
<text><location><page_3><loc_9><loc_14><loc_48><loc_23></location>To ensure that future benchmarks in the document-layout analysis community can be easily compared, we have split up DocLayNet into pre-defined train-, test- and validation-sets. In this way, we can avoid spurious variations in the evaluation scores due to random splitting in train-, test- and validation-sets. We also ensured that less frequent labels are represented in train and test sets in equal proportions.</text>
<footnote><location><page_3><loc_9><loc_11><loc_32><loc_12></location>$^{2}$e.g. AAPL from https://www.annualreports.com/</footnote>
<text><location><page_3><loc_52><loc_80><loc_91><loc_89></location>Table 1 shows the overall frequency and distribution of the labels among the different sets. Importantly, we ensure that subsets are only split on full-document boundaries. This avoids that pages of the same document are spread over train, test and validation set, which can give an undesired evaluation advantage to models and lead to overestimation of their prediction accuracy. We will show the impact of this decision in Section 5.</text>
<text><location><page_3><loc_52><loc_66><loc_91><loc_79></location>In order to accommodate the different types of models currently in use by the community, we provide DocLayNet in an augmented COCO format [16]. This entails the standard COCO ground-truth file (in JSON format) with the associated page images (in PNG format, 1025 × 1025 pixels). Furthermore, custom fields have been added to each COCO record to specify document category, original document filename and page number. In addition, we also provide the original PDF pages, as well as sidecar files containing parsed PDF text and text-cell coordinates (in JSON). All additional files are linked to the primary page images by their matching filenames.</text>
<text><location><page_3><loc_52><loc_26><loc_91><loc_66></location>Despite being cost-intense and far less scalable than automation, human annotation has several benefits over automated groundtruth generation. The first and most obvious reason to leverage human annotations is the freedom to annotate any type of document without requiring a programmatic source. For most PDF documents, the original source document is not available. The latter is not a hard constraint with human annotation, but it is for automated methods. A second reason to use human annotations is that the latter usually provide a more natural interpretation of the page layout. The human-interpreted layout can significantly deviate from the programmatic layout used in typesetting. For example, "invisible" tables might be used solely for aligning text paragraphs on columns. Such typesetting tricks might be interpreted by automated methods incorrectly as an actual table, while the human annotation will interpret it correctly as Text or other styles. The same applies to multi-line text elements, when authors decided to space them as "invisible" list elements without bullet symbols. A third reason to gather ground-truth through human annotation is to estimate a "natural" upper bound on the segmentation accuracy. As we will show in Section 4, certain documents featuring complex layouts can have different but equally acceptable layout interpretations. This natural upper bound for segmentation accuracy can be found by annotating the same pages multiple times by different people and evaluating the inter-annotator agreement. Such a baseline consistency evaluation is very useful to define expectations for a good target accuracy in trained deep neural network models and avoid overfitting (see Table 1). On the flip side, achieving high annotation consistency proved to be a key challenge in human annotation, as we outline in Section 4.</text>
@ -91,7 +89,6 @@
<text><location><page_4><loc_52><loc_53><loc_91><loc_61></location>include publication repositories such as arXiv$^{3}$, government offices, company websites as well as data directory services for financial reports and patents. Scanned documents were excluded wherever possible because they can be rotated or skewed. This would not allow us to perform annotation with rectangular bounding-boxes and therefore complicate the annotation process.</text>
<text><location><page_4><loc_52><loc_36><loc_91><loc_52></location>Preparation work included uploading and parsing the sourced PDF documents in the Corpus Conversion Service (CCS) [22], a cloud-native platform which provides a visual annotation interface and allows for dataset inspection and analysis. The annotation interface of CCS is shown in Figure 3. The desired balance of pages between the different document categories was achieved by selective subsampling of pages with certain desired properties. For example, we made sure to include the title page of each document and bias the remaining page selection to those with figures or tables. The latter was achieved by leveraging pre-trained object detection models from PubLayNet, which helped us estimate how many figures and tables a given page contains.</text>
<text><location><page_4><loc_52><loc_12><loc_91><loc_36></location>Phase 2: Label selection and guideline. We reviewed the collected documents and identified the most common structural features they exhibit. This was achieved by identifying recurrent layout elements and lead us to the definition of 11 distinct class labels. These 11 class labels are Caption , Footnote , Formula , List-item , Pagefooter , Page-header , Picture , Section-header , Table , Text , and Title . Critical factors that were considered for the choice of these class labels were (1) the overall occurrence of the label, (2) the specificity of the label, (3) recognisability on a single page (i.e. no need for context from previous or next page) and (4) overall coverage of the page. Specificity ensures that the choice of label is not ambiguous, while coverage ensures that all meaningful items on a page can be annotated. We refrained from class labels that are very specific to a document category, such as Abstract in the Scientific Articles category. We also avoided class labels that are tightly linked to the semantics of the text. Labels such as Author and Affiliation , as seen in DocBank, are often only distinguishable by discriminating on</text>
<footnote><location><page_4><loc_52><loc_10><loc_60><loc_11></location>$^{3}$https://arxiv.org/</footnote>
<text><location><page_5><loc_9><loc_86><loc_48><loc_89></location>the textual content of an element, which goes beyond visual layout recognition, in particular outside the Scientific Articles category.</text>
<text><location><page_5><loc_9><loc_68><loc_48><loc_86></location>At first sight, the task of visual document-layout interpretation appears intuitive enough to obtain plausible annotations in most cases. However, during early trial-runs in the core team, we observed many cases in which annotators use different annotation styles, especially for documents with challenging layouts. For example, if a figure is presented with subfigures, one annotator might draw a single figure bounding-box, while another might annotate each subfigure separately. The same applies for lists, where one might annotate all list items in one block or each list item separately. In essence, we observed that challenging layouts would be annotated in different but plausible ways. To illustrate this, we show in Figure 4 multiple examples of plausible but inconsistent annotations on the same pages.</text>
<text><location><page_5><loc_9><loc_57><loc_48><loc_68></location>Obviously, this inconsistency in annotations is not desirable for datasets which are intended to be used for model training. To minimise these inconsistencies, we created a detailed annotation guideline. While perfect consistency across 40 annotation staff members is clearly not possible to achieve, we saw a huge improvement in annotation consistency after the introduction of our annotation guideline. A few selected, non-trivial highlights of the guideline are:</text>

6
tests/data/groundtruth/docling_v2/2206.01062.md
View File

@ -66,8 +66,6 @@ In this paper, we present the DocLayNet dataset. It provides pageby-page layout
(4) Redundant Annotations : A fraction of the pages in the DocLayNet data set carry more than one human annotation.
$^{1}$https://developer.ibm.com/exchanges/data/all/doclaynet
This enables experimentation with annotation uncertainty and quality control analysis.
(5) Pre-defined Train-, Test- & Validation-set : Like DocBank, we provide fixed train-, test- & validation-sets to ensure proportional representation of the class-labels. Further, we prevent leakage of unique layouts across sets, which has a large effect on model accuracy scores.
@ -100,8 +98,6 @@ We did not control the document selection with regard to language. The vast majo
To ensure that future benchmarks in the document-layout analysis community can be easily compared, we have split up DocLayNet into pre-defined train-, test- and validation-sets. In this way, we can avoid spurious variations in the evaluation scores due to random splitting in train-, test- and validation-sets. We also ensured that less frequent labels are represented in train and test sets in equal proportions.
$^{2}$e.g. AAPL from https://www.annualreports.com/
Table 1 shows the overall frequency and distribution of the labels among the different sets. Importantly, we ensure that subsets are only split on full-document boundaries. This avoids that pages of the same document are spread over train, test and validation set, which can give an undesired evaluation advantage to models and lead to overestimation of their prediction accuracy. We will show the impact of this decision in Section 5.
In order to accommodate the different types of models currently in use by the community, we provide DocLayNet in an augmented COCO format [16]. This entails the standard COCO ground-truth file (in JSON format) with the associated page images (in PNG format, 1025 × 1025 pixels). Furthermore, custom fields have been added to each COCO record to specify document category, original document filename and page number. In addition, we also provide the original PDF pages, as well as sidecar files containing parsed PDF text and text-cell coordinates (in JSON). All additional files are linked to the primary page images by their matching filenames.
@ -144,8 +140,6 @@ Preparation work included uploading and parsing the sourced PDF documents in the
Phase 2: Label selection and guideline. We reviewed the collected documents and identified the most common structural features they exhibit. This was achieved by identifying recurrent layout elements and lead us to the definition of 11 distinct class labels. These 11 class labels are Caption , Footnote , Formula , List-item , Pagefooter , Page-header , Picture , Section-header , Table , Text , and Title . Critical factors that were considered for the choice of these class labels were (1) the overall occurrence of the label, (2) the specificity of the label, (3) recognisability on a single page (i.e. no need for context from previous or next page) and (4) overall coverage of the page. Specificity ensures that the choice of label is not ambiguous, while coverage ensures that all meaningful items on a page can be annotated. We refrained from class labels that are very specific to a document category, such as Abstract in the Scientific Articles category. We also avoided class labels that are tightly linked to the semantics of the text. Labels such as Author and Affiliation , as seen in DocBank, are often only distinguishable by discriminating on
$^{3}$https://arxiv.org/
the textual content of an element, which goes beyond visual layout recognition, in particular outside the Scientific Articles category.
At first sight, the task of visual document-layout interpretation appears intuitive enough to obtain plausible annotations in most cases. However, during early trial-runs in the core team, we observed many cases in which annotators use different annotation styles, especially for documents with challenging layouts. For example, if a figure is presented with subfigures, one annotator might draw a single figure bounding-box, while another might annotate each subfigure separately. The same applies for lists, where one might annotate all list items in one block or each list item separately. In essence, we observed that challenging layouts would be annotated in different but plausible ways. To illustrate this, we show in Figure 4 multiple examples of plausible but inconsistent annotations on the same pages.

2
tests/data/groundtruth/docling_v2/redp5110.doctags.txt
View File

@ -305,8 +305,6 @@
<list_item><location><page_17><loc_22><loc_32><loc_41><loc_33></location>GLYPH<SM590000> Security fundamentals</list_item>
<list_item><location><page_17><loc_22><loc_30><loc_46><loc_32></location>GLYPH<SM590000> Current state of IBM i security</list_item>
<list_item><location><page_17><loc_22><loc_29><loc_43><loc_30></location>GLYPH<SM590000> DB2 for i security controls</list_item>
<footnote><location><page_17><loc_22><loc_8><loc_42><loc_10></location>$^{1 }$http://www.idtheftcenter.org</footnote>
<footnote><location><page_17><loc_22><loc_7><loc_38><loc_8></location>$^{2 }$http://www.ponemon.org /</footnote>
<section_header><location><page_18><loc_11><loc_89><loc_44><loc_91></location>1.1 Security fundamentals</section_header>
<text><location><page_18><loc_22><loc_84><loc_89><loc_87></location>Before reviewing database security techniques, there are two fundamental steps in securing information assets that must be described:</text>
<list_item><location><page_18><loc_22><loc_77><loc_89><loc_83></location>GLYPH<SM590000> First, and most important, is the definition of a company's security policy . Without a security policy, there is no definition of what are acceptable practices for using, accessing, and storing information by who, what, when, where, and how. A security policy should minimally address three things: confidentiality, integrity, and availability.</list_item>

4
tests/data/groundtruth/docling_v2/redp5110.md
View File

@ -423,10 +423,6 @@ GLYPH<SM590000> Current state of IBM i security
GLYPH<SM590000> DB2 for i security controls
$^{1 }$http://www.idtheftcenter.org
$^{2 }$http://www.ponemon.org /
## 1.1 Security fundamentals
Before reviewing database security techniques, there are two fundamental steps in securing information assets that must be described:

3
tests/data/groundtruth/docling_v2/redp5695.doctags.txt
View File

@ -23,7 +23,6 @@
<text><location><page_3><loc_22><loc_41><loc_89><loc_48></location>With IBM Cloud Pakfi for Data on IBM Z, enterprises can modernize their data infrastructure, develop, and deploy machine learning (ML) and AI models, and instantiate highly efficient analytics deployment on IBM LinuxONE. Enterprises can create cutting-edge, intelligent, and interactive applications with embedded AI, colocate data with commercial applications, and use AI to make inferences.</text>
<text><location><page_3><loc_22><loc_32><loc_89><loc_39></location>This IBM Redguide publication presents a high-level overview of IBM Z. It describes IBM Cloud Pak for Data (CP4D) on IBM Z and IBM LinuxONE, the different features that are supported on the platform, and how the associated features can help enterprise customers in building AI and ML models by using core transactional data, which results in decreased latency and increased throughput.</text>
<text><location><page_3><loc_22><loc_22><loc_89><loc_31></location>This publication highlights real-time CP4D on IBM Z use cases. Real-time Clearing and Settlement Transactions, Trustworthy AI and its Role in Day-To-Day Monitoring, and the Prevention of Retail Crimes are use cases that are described in this publication. Using CP4D on IBM Z and LinuxONE, this publication shows how businesses can implement a highly efficient analytics deployment that minimizes latency, cost inefficiencies, and potential security exposures that are connected with data transportation.</text>
<footnote><location><page_3><loc_22><loc_7><loc_63><loc_8></location>$^{1 }$https://www.bcbsm.com/health-care-fraud/fraud-statistics.html</footnote>
<section_header><location><page_4><loc_11><loc_89><loc_35><loc_91></location>IBM Z: An overview</section_header>
<text><location><page_4><loc_22><loc_80><loc_88><loc_87></location>Ever wonder how many transactions a bank processes per day? What about the pace at which these transactions happen? According to an IBMfi report, 44 of 50 of the world's top banks use IBM Z mainframes for these daily transactions.$^{2}$ IBM Z is a platform that is designed for voluminous data, maximum security, real-time transaction analysis, and cost efficiency.</text>
<text><location><page_4><loc_22><loc_75><loc_84><loc_78></location>The most recent platform for IBM Z is IBM z16™. The IBM z16 supports the following features:</text>
@ -36,7 +35,6 @@
<text><location><page_4><loc_22><loc_58><loc_85><loc_61></location>With these features, enterprises can upgrade applications while preserving secure and resilient data.</text>
<text><location><page_4><loc_22><loc_55><loc_71><loc_57></location>To learn more about these features, see the IBM z16 product page.</text>
<text><location><page_4><loc_22><loc_53><loc_68><loc_54></location>Figure 1 on page 3 shows a picture of the IBM z16 mainframe.</text>
<footnote><location><page_4><loc_22><loc_7><loc_51><loc_8></location>$^{2 }$https://www.ibm.com/case-studies/bankwest/</footnote>
<caption><location><page_5><loc_22><loc_42><loc_34><loc_43></location>Figure 1 IBM z16</caption>
<figure>
<location><page_5><loc_22><loc_44><loc_71><loc_90></location>
@ -183,7 +181,6 @@
<list_item><location><page_17><loc_22><loc_37><loc_86><loc_40></location>GLYPH<SM590000> Monitor the AI models with Watson OpenScale on CP4D on Red Hat OpenShift on a virtual machine on IBM Z.</list_item>
<list_item><location><page_17><loc_22><loc_28><loc_89><loc_36></location>GLYPH<SM590000> Enterprises can develop AI models by creating and training models by using Watson Studio and development tools such as Jupyter Notebook or JupyterLab, and then deploying the model onto WML on CP4D on Red Hat OpenShift on a virtual machine on IBM Z. Then, these enterprises can achieve end-end AI governance by running AI Factsheets, IBM Watson OpenScale, and IBM Watson OpenPagesfi on CP4D on x86.</list_item>
<text><location><page_17><loc_22><loc_26><loc_84><loc_27></location>Figure 9 on page 16 shows the end-to-end flow for a remote AI governance solution.</text>
<footnote><location><page_17><loc_22><loc_7><loc_68><loc_8></location>$^{3 }$https://www.proofpoint.com/us/threat-reference/regulatory-compliance</footnote>
<caption><location><page_18><loc_11><loc_62><loc_48><loc_63></location>Figure 9 Remote AI governance solution end-to-end flow</caption>
<figure>
<location><page_18><loc_11><loc_63><loc_89><loc_90></location>

6
tests/data/groundtruth/docling_v2/redp5695.md
View File

@ -30,8 +30,6 @@ This IBM Redguide publication presents a high-level overview of IBM Z. It descri
This publication highlights real-time CP4D on IBM Z use cases. Real-time Clearing and Settlement Transactions, Trustworthy AI and its Role in Day-To-Day Monitoring, and the Prevention of Retail Crimes are use cases that are described in this publication. Using CP4D on IBM Z and LinuxONE, this publication shows how businesses can implement a highly efficient analytics deployment that minimizes latency, cost inefficiencies, and potential security exposures that are connected with data transportation.
$^{1 }$https://www.bcbsm.com/health-care-fraud/fraud-statistics.html
## IBM Z: An overview
Ever wonder how many transactions a bank processes per day? What about the pace at which these transactions happen? According to an IBMfi report, 44 of 50 of the world's top banks use IBM Z mainframes for these daily transactions.$^{2}$ IBM Z is a platform that is designed for voluminous data, maximum security, real-time transaction analysis, and cost efficiency.
@ -56,8 +54,6 @@ To learn more about these features, see the IBM z16 product page.
Figure 1 on page 3 shows a picture of the IBM z16 mainframe.
$^{2 }$https://www.ibm.com/case-studies/bankwest/
Figure 1 IBM z16
<!-- image -->
@ -318,8 +314,6 @@ GLYPH<SM590000> Enterprises can develop AI models by creating and training model
Figure 9 on page 16 shows the end-to-end flow for a remote AI governance solution.
$^{3 }$https://www.proofpoint.com/us/threat-reference/regulatory-compliance
Figure 9 Remote AI governance solution end-to-end flow
<!-- image -->

2
tests/test_e2e_conversion.py
View File

@ -9,7 +9,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
GENERATE_V1 = False
GENERATE_V2 = True
GENERATE_V2 = False
def get_pdf_paths():