added hf_xet

pyproject.toml

@@ -6,6 +6,7 @@ dependencies = [
     "bertopic",
     "contractions",
     "en-core-web-sm",
+    "hf-xet>=1.1.5",
     "joblib",
     "jupyterlab>=4.4.2",
     "langchain-core",

uv.lock

@@ -14,6 +14,7 @@ dependencies = [
     { name = "bertopic" },
     { name = "contractions" },
     { name = "en-core-web-sm" },
+    { name = "hf-xet" },
     { name = "joblib" },
     { name = "jupyterlab" },
     { name = "langchain-core" },
@@ -40,6 +41,7 @@ requires-dist = [
     { name = "bertopic" },
     { name = "contractions" },
     { name = "en-core-web-sm", url = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl" },
+    { name = "hf-xet", specifier = ">=1.1.5" },
     { name = "joblib" },
     { name = "jupyterlab", specifier = ">=4.4.2" },
     { name = "langchain-core" },
@@ -821,6 +823,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c0/cb/6b4254f8a33e075118512e55acf3485c155ea52c6c35d69a985bdc59297c/hdbscan-0.8.40-cp312-cp312-win_amd64.whl", hash = "sha256:1b55a935ed7b329adac52072e1c4028979dfc54312ca08de2deece9c97d6ebb1", size = 726198, upload-time = "2024-11-18T16:18:09.99Z" },
 ]
 
+[[package]]
+name = "hf-xet"
+version = "1.1.5"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ed/d4/7685999e85945ed0d7f0762b686ae7015035390de1161dcea9d5276c134c/hf_xet-1.1.5.tar.gz", hash = "sha256:69ebbcfd9ec44fdc2af73441619eeb06b94ee34511bbcf57cd423820090f5694", size = 495969, upload-time = "2025-06-20T21:48:38.007Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/00/89/a1119eebe2836cb25758e7661d6410d3eae982e2b5e974bcc4d250be9012/hf_xet-1.1.5-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:f52c2fa3635b8c37c7764d8796dfa72706cc4eded19d638331161e82b0792e23", size = 2687929, upload-time = "2025-06-20T21:48:32.284Z" },
+    { url = "https://files.pythonhosted.org/packages/de/5f/2c78e28f309396e71ec8e4e9304a6483dcbc36172b5cea8f291994163425/hf_xet-1.1.5-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:9fa6e3ee5d61912c4a113e0708eaaef987047616465ac7aa30f7121a48fc1af8", size = 2556338, upload-time = "2025-06-20T21:48:30.079Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/2f/6cad7b5fe86b7652579346cb7f85156c11761df26435651cbba89376cd2c/hf_xet-1.1.5-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc874b5c843e642f45fd85cda1ce599e123308ad2901ead23d3510a47ff506d1", size = 3102894, upload-time = "2025-06-20T21:48:28.114Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/54/0fcf2b619720a26fbb6cc941e89f2472a522cd963a776c089b189559447f/hf_xet-1.1.5-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:dbba1660e5d810bd0ea77c511a99e9242d920790d0e63c0e4673ed36c4022d18", size = 3002134, upload-time = "2025-06-20T21:48:25.906Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/92/1d351ac6cef7c4ba8c85744d37ffbfac2d53d0a6c04d2cabeba614640a78/hf_xet-1.1.5-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ab34c4c3104133c495785d5d8bba3b1efc99de52c02e759cf711a91fd39d3a14", size = 3171009, upload-time = "2025-06-20T21:48:33.987Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/65/4b2ddb0e3e983f2508528eb4501288ae2f84963586fbdfae596836d5e57a/hf_xet-1.1.5-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:83088ecea236d5113de478acb2339f92c95b4fb0462acaa30621fac02f5a534a", size = 3279245, upload-time = "2025-06-20T21:48:36.051Z" },
+    { url = "https://files.pythonhosted.org/packages/f0/55/ef77a85ee443ae05a9e9cba1c9f0dd9241eb42da2aeba1dc50f51154c81a/hf_xet-1.1.5-cp37-abi3-win_amd64.whl", hash = "sha256:73e167d9807d166596b4b2f0b585c6d5bd84a26dea32843665a8b58f6edba245", size = 2738931, upload-time = "2025-06-20T21:48:39.482Z" },
+]
+
 [[package]]
 name = "htbuilder"
 version = "0.9.0"