Start addition of NLP service

# Conflicts:
#	pdm.lock
#	pyproject.toml
#	src/de_quoi_parle_le_monde/main.py

pdm.lock

@@ -5,7 +5,7 @@
 groups = ["default"]
 strategy = ["cross_platform", "inherit_metadata"]
 lock_version = "4.4.1"
-content_hash = "sha256:4c270a78a0a28a5426bc46b9fe833d8ebd04d1352497613cc5837cc9e71bd4b8"
+content_hash = "sha256:8c1cb475ddfebdb04754ce348d6c6fce8c808c980b06ee0935dca722cfc4de58"
 
 [[package]]
 name = "aioboto3"
@@ -185,13 +185,24 @@ files = [
     {file = "aiosqlite-0.20.0.tar.gz", hash = "sha256:6d35c8c256637f4672f843c31021464090805bf925385ac39473fb16eaaca3d7"},
 ]
 
+[[package]]
+name = "annotated-types"
+version = "0.6.0"
+requires_python = ">=3.8"
+summary = "Reusable constraint types to use with typing.Annotated"
+groups = ["default"]
+files = [
+    {file = "annotated_types-0.6.0-py3-none-any.whl", hash = "sha256:0641064de18ba7a25dee8f96403ebc39113d0cb953a01429249d5c7564666a43"},
+    {file = "annotated_types-0.6.0.tar.gz", hash = "sha256:563339e807e53ffd9c267e99fc6d9ea23eb8443c08f112651963e24e22f84a5d"},
+]
+
 [[package]]
 name = "async-timeout"
 version = "4.0.3"
 requires_python = ">=3.7"
 summary = "Timeout context manager for asyncio programs"
 groups = ["default"]
-marker = "python_full_version <= \"3.11.2\""
+marker = "python_full_version < \"3.11.3\""
 files = [
     {file = "async-timeout-4.0.3.tar.gz", hash = "sha256:4640d96be84d82d02ed59ea2b7105a0f7b33abe8703703cd0ab0bf87c427522f"},
     {file = "async_timeout-4.0.3-py3-none-any.whl", hash = "sha256:7405140ff1230c310e51dc27b3145b9092d659ce68ff733fb0cefe3ee42be028"},
@@ -222,6 +233,23 @@ files = [
     {file = "beautifulsoup4-4.12.3.tar.gz", hash = "sha256:74e3d1928edc070d21748185c46e3fb33490f22f52a3addee9aee0f4f7781051"},
 ]
 
+[[package]]
+name = "blis"
+version = "0.7.11"
+summary = "The Blis BLAS-like linear algebra library, as a self-contained C-extension."
+groups = ["default"]
+dependencies = [
+    "numpy>=1.19.0; python_version >= \"3.9\"",
+]
+files = [
+    {file = "blis-0.7.11-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1b68df4d01d62f9adaef3dad6f96418787265a6878891fc4e0fabafd6d02afba"},
+    {file = "blis-0.7.11-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:162e60d941a8151418d558a94ee5547cb1bbeed9f26b3b6f89ec9243f111a201"},
+    {file = "blis-0.7.11-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:686a7d0111d5ba727cd62f374748952fd6eb74701b18177f525b16209a253c01"},
+    {file = "blis-0.7.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0421d6e44cda202b113a34761f9a062b53f8c2ae8e4ec8325a76e709fca93b6e"},
+    {file = "blis-0.7.11-cp311-cp311-win_amd64.whl", hash = "sha256:0dc9dcb3843045b6b8b00432409fd5ee96b8344a324e031bfec7303838c41a1a"},
+    {file = "blis-0.7.11.tar.gz", hash = "sha256:cec6d48f75f7ac328ae1b6fbb372dde8c8a57c89559172277f66e01ff08d4d42"},
+]
+
 [[package]]
 name = "boto3"
 version = "1.34.34"
@@ -254,6 +282,17 @@ files = [
     {file = "botocore-1.34.34.tar.gz", hash = "sha256:54093dc97372bb7683f5c61a279aa8240408abf3b2cc494ae82a9a90c1b784b5"},
 ]
 
+[[package]]
+name = "catalogue"
+version = "2.0.10"
+requires_python = ">=3.6"
+summary = "Super lightweight function registries for your library"
+groups = ["default"]
+files = [
+    {file = "catalogue-2.0.10-py3-none-any.whl", hash = "sha256:58c2de0020aa90f4a2da7dfad161bf7b3b054c86a5f09fcedc0b2b740c109a9f"},
+    {file = "catalogue-2.0.10.tar.gz", hash = "sha256:4f56daa940913d3f09d589c191c74e5a6d51762b3a9e37dd53b7437afd6cda15"},
+]
+
 [[package]]
 name = "cattrs"
 version = "23.2.3"
@@ -305,18 +344,72 @@ files = [
     {file = "charset_normalizer-3.3.2-py3-none-any.whl", hash = "sha256:3e4d1f6587322d2788836a99c69062fbb091331ec940e02d12d179c1d53e25fc"},
 ]
 
+[[package]]
+name = "click"
+version = "8.1.7"
+requires_python = ">=3.7"
+summary = "Composable command line interface toolkit"
+groups = ["default"]
+dependencies = [
+    "colorama; platform_system == \"Windows\"",
+]
+files = [
+    {file = "click-8.1.7-py3-none-any.whl", hash = "sha256:ae74fb96c20a0277a1d615f1e4d73c8414f5a98db8b799a7931d1582f3390c28"},
+    {file = "click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de"},
+]
+
+[[package]]
+name = "cloudpathlib"
+version = "0.16.0"
+requires_python = ">=3.7"
+summary = "pathlib-style classes for cloud storage services."
+groups = ["default"]
+files = [
+    {file = "cloudpathlib-0.16.0-py3-none-any.whl", hash = "sha256:f46267556bf91f03db52b5df7a152548596a15aabca1c8731ef32b0b25a1a6a3"},
+    {file = "cloudpathlib-0.16.0.tar.gz", hash = "sha256:cdfcd35d46d529587d744154a0bdf962aca953b725c8784cd2ec478354ea63a3"},
+]
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
 requires_python = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
 summary = "Cross-platform colored terminal text."
 groups = ["default"]
-marker = "sys_platform == \"win32\""
+marker = "sys_platform == \"win32\" or platform_system == \"Windows\""
 files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
 
+[[package]]
+name = "confection"
+version = "0.1.4"
+requires_python = ">=3.6"
+summary = "The sweetest config system for Python"
+groups = ["default"]
+dependencies = [
+    "pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4",
+    "srsly<3.0.0,>=2.4.0",
+]
+files = [
+    {file = "confection-0.1.4-py3-none-any.whl", hash = "sha256:a658818d004939069c3e2b3db74a2cb9d956a5e61a1c9ad61788e0ee09a7090f"},
+    {file = "confection-0.1.4.tar.gz", hash = "sha256:e80f22fd008b5231a2e8852fac6de9e28f2276a04031d0536cff74fe4a990c8f"},
+]
+
+[[package]]
+name = "cymem"
+version = "2.0.8"
+summary = "Manage calls to calloc/free through Cython"
+groups = ["default"]
+files = [
+    {file = "cymem-2.0.8-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6b84b780d52cb2db53d4494fe0083c4c5ee1f7b5380ceaea5b824569009ee5bd"},
+    {file = "cymem-2.0.8-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:0d5f83dc3cb5a39f0e32653cceb7c8ce0183d82f1162ca418356f4a8ed9e203e"},
+    {file = "cymem-2.0.8-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ac218cf8a43a761dc6b2f14ae8d183aca2bbb85b60fe316fd6613693b2a7914"},
+    {file = "cymem-2.0.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42c993589d1811ec665d37437d5677b8757f53afadd927bf8516ac8ce2d3a50c"},
+    {file = "cymem-2.0.8-cp311-cp311-win_amd64.whl", hash = "sha256:ab3cf20e0eabee9b6025ceb0245dadd534a96710d43fb7a91a35e0b9e672ee44"},
+    {file = "cymem-2.0.8.tar.gz", hash = "sha256:8fb09d222e21dcf1c7e907dc85cf74501d4cea6c4ed4ac6c9e016f98fb59cbbf"},
+]
+
 [[package]]
 name = "dnspython"
 version = "2.6.1"
@@ -328,6 +421,19 @@ files = [
     {file = "dnspython-2.6.1.tar.gz", hash = "sha256:e8f0f9c23a7b7cb99ded64e6c3a6f3e701d78f50c55e002b839dea7225cff7cc"},
 ]
 
+[[package]]
+name = "fr-core-news-sm"
+version = "3.7.0"
+url = "https://github.com/explosion/spacy-models/releases/download/fr_core_news_sm-3.7.0/fr_core_news_sm-3.7.0.tar.gz"
+summary = "French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer."
+groups = ["default"]
+dependencies = [
+    "spacy<3.8.0,>=3.7.0",
+]
+files = [
+    {file = "fr_core_news_sm-3.7.0.tar.gz", hash = "sha256:abc17ce92ed8cfacd006c6b951e7c8dada05f0e4104b2884872e6898da57cbc5"},
+]
+
 [[package]]
 name = "frozenlist"
 version = "1.4.1"
@@ -376,6 +482,20 @@ files = [
     {file = "itsdangerous-2.1.2.tar.gz", hash = "sha256:5dbbc68b317e5e42f327f9021763545dc3fc3bfe22e6deb96aaf1fc38874156a"},
 ]
 
+[[package]]
+name = "jinja2"
+version = "3.1.3"
+requires_python = ">=3.7"
+summary = "A very fast and expressive template engine."
+groups = ["default"]
+dependencies = [
+    "MarkupSafe>=2.0",
+]
+files = [
+    {file = "Jinja2-3.1.3-py3-none-any.whl", hash = "sha256:7d6d50dd97d52cbc355597bd845fabfbac3f551e1f99619e39a35ce8c370b5fa"},
+    {file = "Jinja2-3.1.3.tar.gz", hash = "sha256:ac8bd6544d4bb2c9792bf3a159e80bba8fda7f07e81bc3aed565432d5925ba90"},
+]
+
 [[package]]
 name = "jmespath"
 version = "1.0.1"
@@ -387,6 +507,17 @@ files = [
     {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"},
 ]
 
+[[package]]
+name = "langcodes"
+version = "3.3.0"
+requires_python = ">=3.6"
+summary = "Tools for labeling human languages with IETF language tags"
+groups = ["default"]
+files = [
+    {file = "langcodes-3.3.0-py3-none-any.whl", hash = "sha256:4d89fc9acb6e9c8fdef70bcdf376113a3db09b67285d9e1d534de6d8818e7e69"},
+    {file = "langcodes-3.3.0.tar.gz", hash = "sha256:794d07d5a28781231ac335a1561b8442f8648ca07cd518310aeb45d6f0807ef6"},
+]
+
 [[package]]
 name = "loguru"
 version = "0.7.2"
@@ -434,6 +565,26 @@ files = [
     {file = "lxml-5.1.0.tar.gz", hash = "sha256:3eea6ed6e6c918e468e693c41ef07f3c3acc310b70ddd9cc72d9ef84bc9564ca"},
 ]
 
+[[package]]
+name = "markupsafe"
+version = "2.1.5"
+requires_python = ">=3.7"
+summary = "Safely add untrusted strings to HTML/XML markup."
+groups = ["default"]
+files = [
+    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:629ddd2ca402ae6dbedfceeba9c46d5f7b2a61d9749597d4307f943ef198fc1f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5b7b716f97b52c5a14bffdf688f971b2d5ef4029127f1ad7a513973cfd818df2"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ec585f69cec0aa07d945b20805be741395e28ac1627333b1c5b0105962ffced"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b91c037585eba9095565a3556f611e3cbfaa42ca1e865f7b8015fe5c7336d5a5"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7502934a33b54030eaf1194c21c692a534196063db72176b0c4028e140f8f32c"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0e397ac966fdf721b2c528cf028494e86172b4feba51d65f81ffd65c63798f3f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:c061bb86a71b42465156a3ee7bd58c8c2ceacdbeb95d05a99893e08b8467359a"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:3a57fdd7ce31c7ff06cdfbf31dafa96cc533c21e443d57f5b1ecc6cdc668ec7f"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-win32.whl", hash = "sha256:397081c1a0bfb5124355710fe79478cdbeb39626492b15d399526ae53422b906"},
+    {file = "MarkupSafe-2.1.5-cp311-cp311-win_amd64.whl", hash = "sha256:2b7c57a4dfc4f16f7142221afe5ba4e093e09e728ca65c51f5620c9aaeb9a617"},
+    {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"},
+]
+
 [[package]]
 name = "motor"
 version = "3.3.2"
@@ -474,6 +625,54 @@ files = [
     {file = "multidict-6.0.5.tar.gz", hash = "sha256:f7e301075edaf50500f0b341543c41194d8df3ae5caf4702f2095f3ca73dd8da"},
 ]
 
+[[package]]
+name = "murmurhash"
+version = "1.0.10"
+requires_python = ">=3.6"
+summary = "Cython bindings for MurmurHash"
+groups = ["default"]
+files = [
+    {file = "murmurhash-1.0.10-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:90ed37ee2cace9381b83d56068334f77e3e30bc521169a1f886a2a2800e965d6"},
+    {file = "murmurhash-1.0.10-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:22e9926fdbec9d24ced9b0a42f0fee68c730438be3cfb00c2499fd495caec226"},
+    {file = "murmurhash-1.0.10-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:54bfbfd68baa99717239b8844600db627f336a08b1caf4df89762999f681cdd1"},
+    {file = "murmurhash-1.0.10-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18b9d200a09d48ef67f6840b77c14f151f2b6c48fd69661eb75c7276ebdb146c"},
+    {file = "murmurhash-1.0.10-cp311-cp311-win_amd64.whl", hash = "sha256:e5d7cfe392c0a28129226271008e61e77bf307afc24abf34f386771daa7b28b0"},
+    {file = "murmurhash-1.0.10.tar.gz", hash = "sha256:5282aab1317804c6ebd6dd7f69f15ba9075aee671c44a34be2bde0f1b11ef88a"},
+]
+
+[[package]]
+name = "numpy"
+version = "1.26.4"
+requires_python = ">=3.9"
+summary = "Fundamental package for array computing in Python"
+groups = ["default"]
+marker = "python_version >= \"3.9\""
+files = [
+    {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"},
+    {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"},
+    {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"},
+    {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"},
+    {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
+]
+
+[[package]]
+name = "packaging"
+version = "24.0"
+requires_python = ">=3.7"
+summary = "Core utilities for Python packages"
+groups = ["default"]
+files = [
+    {file = "packaging-24.0-py3-none-any.whl", hash = "sha256:2ddfb553fdf02fb784c234c7ba6ccc288296ceabec964ad2eae3777778130bc5"},
+    {file = "packaging-24.0.tar.gz", hash = "sha256:eb82c5e3e56209074766e6885bb04b8c38a0c015d0a30036ebe7ece34c9989e9"},
+]
+
 [[package]]
 name = "platformdirs"
 version = "4.2.0"
@@ -485,6 +684,83 @@ files = [
     {file = "platformdirs-4.2.0.tar.gz", hash = "sha256:ef0cc731df711022c174543cb70a9b5bd22e5a9337c8624ef2c2ceb8ddad8768"},
 ]
 
+[[package]]
+name = "preshed"
+version = "3.0.9"
+requires_python = ">=3.6"
+summary = "Cython hash table that trusts the keys are pre-hashed"
+groups = ["default"]
+dependencies = [
+    "cymem<2.1.0,>=2.0.2",
+    "murmurhash<1.1.0,>=0.28.0",
+]
+files = [
+    {file = "preshed-3.0.9-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e7c2364da27f2875524ce1ca754dc071515a9ad26eb5def4c7e69129a13c9a59"},
+    {file = "preshed-3.0.9-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:182138033c0730c683a6d97e567ceb8a3e83f3bff5704f300d582238dbd384b3"},
+    {file = "preshed-3.0.9-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:345a10be3b86bcc6c0591d343a6dc2bfd86aa6838c30ced4256dfcfa836c3a64"},
+    {file = "preshed-3.0.9-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:51d0192274aa061699b284f9fd08416065348edbafd64840c3889617ee1609de"},
+    {file = "preshed-3.0.9-cp311-cp311-win_amd64.whl", hash = "sha256:96b857d7a62cbccc3845ac8c41fd23addf052821be4eb987f2eb0da3d8745aa1"},
+    {file = "preshed-3.0.9.tar.gz", hash = "sha256:721863c5244ffcd2651ad0928951a2c7c77b102f4e11a251ad85d37ee7621660"},
+]
+
+[[package]]
+name = "pydantic"
+version = "2.6.4"
+requires_python = ">=3.8"
+summary = "Data validation using Python type hints"
+groups = ["default"]
+dependencies = [
+    "annotated-types>=0.4.0",
+    "pydantic-core==2.16.3",
+    "typing-extensions>=4.6.1",
+]
+files = [
+    {file = "pydantic-2.6.4-py3-none-any.whl", hash = "sha256:cc46fce86607580867bdc3361ad462bab9c222ef042d3da86f2fb333e1d916c5"},
+    {file = "pydantic-2.6.4.tar.gz", hash = "sha256:b1704e0847db01817624a6b86766967f552dd9dbf3afba4004409f908dcc84e6"},
+]
+
+[[package]]
+name = "pydantic-core"
+version = "2.16.3"
+requires_python = ">=3.8"
+summary = ""
+groups = ["default"]
+dependencies = [
+    "typing-extensions!=4.7.0,>=4.6.0",
+]
+files = [
+    {file = "pydantic_core-2.16.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:519ae0312616026bf4cedc0fe459e982734f3ca82ee8c7246c19b650b60a5ee4"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:b3992a322a5617ded0a9f23fd06dbc1e4bd7cf39bc4ccf344b10f80af58beacd"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8d62da299c6ecb04df729e4b5c52dc0d53f4f8430b4492b93aa8de1f541c4aac"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2acca2be4bb2f2147ada8cac612f8a98fc09f41c89f87add7256ad27332c2fda"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1b662180108c55dfbf1280d865b2d116633d436cfc0bba82323554873967b340"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e7c6ed0dc9d8e65f24f5824291550139fe6f37fac03788d4580da0d33bc00c97"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a6b1bb0827f56654b4437955555dc3aeeebeddc47c2d7ed575477f082622c49e"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e56f8186d6210ac7ece503193ec84104da7ceb98f68ce18c07282fcc2452e76f"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:936e5db01dd49476fa8f4383c259b8b1303d5dd5fb34c97de194560698cc2c5e"},
+    {file = "pydantic_core-2.16.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:33809aebac276089b78db106ee692bdc9044710e26f24a9a2eaa35a0f9fa70ba"},
+    {file = "pydantic_core-2.16.3-cp311-none-win32.whl", hash = "sha256:ded1c35f15c9dea16ead9bffcde9bb5c7c031bff076355dc58dcb1cb436c4721"},
+    {file = "pydantic_core-2.16.3-cp311-none-win_amd64.whl", hash = "sha256:d89ca19cdd0dd5f31606a9329e309d4fcbb3df860960acec32630297d61820df"},
+    {file = "pydantic_core-2.16.3-cp311-none-win_arm64.whl", hash = "sha256:6162f8d2dc27ba21027f261e4fa26f8bcb3cf9784b7f9499466a311ac284b5b9"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:36fa178aacbc277bc6b62a2c3da95226520da4f4e9e206fdf076484363895d2c"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:dcca5d2bf65c6fb591fff92da03f94cd4f315972f97c21975398bd4bd046854a"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2a72fb9963cba4cd5793854fd12f4cfee731e86df140f59ff52a49b3552db241"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b60cc1a081f80a2105a59385b92d82278b15d80ebb3adb200542ae165cd7d183"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:cbcc558401de90a746d02ef330c528f2e668c83350f045833543cd57ecead1ad"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:fee427241c2d9fb7192b658190f9f5fd6dfe41e02f3c1489d2ec1e6a5ab1e04a"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f4cb85f693044e0f71f394ff76c98ddc1bc0953e48c061725e540396d5c8a2e1"},
+    {file = "pydantic_core-2.16.3-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:b29eeb887aa931c2fcef5aa515d9d176d25006794610c264ddc114c053bf96fe"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:a425479ee40ff021f8216c9d07a6a3b54b31c8267c6e17aa88b70d7ebd0e5e5b"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:5c5cbc703168d1b7a838668998308018a2718c2130595e8e190220238addc96f"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99b6add4c0b39a513d323d3b93bc173dac663c27b99860dd5bf491b240d26137"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75f76ee558751746d6a38f89d60b6228fa174e5172d143886af0f85aa306fd89"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:00ee1c97b5364b84cb0bd82e9bbf645d5e2871fb8c58059d158412fee2d33d8a"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:287073c66748f624be4cef893ef9174e3eb88fe0b8a78dc22e88eca4bc357ca6"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:ed25e1835c00a332cb10c683cd39da96a719ab1dfc08427d476bce41b92531fc"},
+    {file = "pydantic_core-2.16.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:86b3d0033580bd6bbe07590152007275bd7af95f98eaa5bd36f3da219dcd93da"},
+    {file = "pydantic_core-2.16.3.tar.gz", hash = "sha256:1cac689f80a3abab2d3c0048b29eea5751114054f032a941a32de4c852c59cad"},
+]
+
 [[package]]
 name = "pymongo"
 version = "4.6.2"
@@ -508,7 +784,7 @@ files = [
 
 [[package]]
 name = "python-dateutil"
-version = "2.8.2"
+version = "2.9.0.post0"
 requires_python = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
 summary = "Extensions to the standard Python datetime module"
 groups = ["default"]
@@ -516,22 +792,22 @@ dependencies = [
     "six>=1.5",
 ]
 files = [
-    {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
-    {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
+    {file = "python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3"},
+    {file = "python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427"},
 ]
 
 [[package]]
 name = "redis"
-version = "5.0.1"
+version = "5.0.3"
 requires_python = ">=3.7"
 summary = "Python client for Redis database and key-value store"
 groups = ["default"]
 dependencies = [
-    "async-timeout>=4.0.2; python_full_version <= \"3.11.2\"",
+    "async-timeout>=4.0.3; python_full_version < \"3.11.3\"",
 ]
 files = [
-    {file = "redis-5.0.1-py3-none-any.whl", hash = "sha256:ed4802971884ae19d640775ba3b03aa2e7bd5e8fb8dfaed2decce4d0fc48391f"},
-    {file = "redis-5.0.1.tar.gz", hash = "sha256:0dab495cd5753069d3bc650a0dde8a8f9edde16fc5691b689a566eda58100d0f"},
+    {file = "redis-5.0.3-py3-none-any.whl", hash = "sha256:5da9b8fe9e1254293756c16c008e8620b3d15fcc6dde6babde9541850e72a32d"},
+    {file = "redis-5.0.3.tar.gz", hash = "sha256:4973bae7444c0fbed64a06b87446f79361cb7e4ec1538c022d696ed7a5015580"},
 ]
 
 [[package]]
@@ -572,33 +848,33 @@ files = [
 
 [[package]]
 name = "ruff"
-version = "0.2.2"
+version = "0.3.4"
 requires_python = ">=3.7"
 summary = "An extremely fast Python linter and code formatter, written in Rust."
 groups = ["default"]
 files = [
-    {file = "ruff-0.2.2-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:0a9efb032855ffb3c21f6405751d5e147b0c6b631e3ca3f6b20f917572b97eb6"},
-    {file = "ruff-0.2.2-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:d450b7fbff85913f866a5384d8912710936e2b96da74541c82c1b458472ddb39"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ecd46e3106850a5c26aee114e562c329f9a1fbe9e4821b008c4404f64ff9ce73"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5e22676a5b875bd72acd3d11d5fa9075d3a5f53b877fe7b4793e4673499318ba"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1695700d1e25a99d28f7a1636d85bafcc5030bba9d0578c0781ba1790dbcf51c"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:b0c232af3d0bd8f521806223723456ffebf8e323bd1e4e82b0befb20ba18388e"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f63d96494eeec2fc70d909393bcd76c69f35334cdbd9e20d089fb3f0640216ca"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6a61ea0ff048e06de273b2e45bd72629f470f5da8f71daf09fe481278b175001"},
-    {file = "ruff-0.2.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5e1439c8f407e4f356470e54cdecdca1bd5439a0673792dbe34a2b0a551a2fe3"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:940de32dc8853eba0f67f7198b3e79bc6ba95c2edbfdfac2144c8235114d6726"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:0c126da55c38dd917621552ab430213bdb3273bb10ddb67bc4b761989210eb6e"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_i686.whl", hash = "sha256:3b65494f7e4bed2e74110dac1f0d17dc8e1f42faaa784e7c58a98e335ec83d7e"},
-    {file = "ruff-0.2.2-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:1ec49be4fe6ddac0503833f3ed8930528e26d1e60ad35c2446da372d16651ce9"},
-    {file = "ruff-0.2.2-py3-none-win32.whl", hash = "sha256:d920499b576f6c68295bc04e7b17b6544d9d05f196bb3aac4358792ef6f34325"},
-    {file = "ruff-0.2.2-py3-none-win_amd64.whl", hash = "sha256:cc9a91ae137d687f43a44c900e5d95e9617cb37d4c989e462980ba27039d239d"},
-    {file = "ruff-0.2.2-py3-none-win_arm64.whl", hash = "sha256:c9d15fc41e6054bfc7200478720570078f0b41c9ae4f010bcc16bd6f4d1aacdd"},
-    {file = "ruff-0.2.2.tar.gz", hash = "sha256:e62ed7f36b3068a30ba39193a14274cd706bc486fad521276458022f7bccb31d"},
+    {file = "ruff-0.3.4-py3-none-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:60c870a7d46efcbc8385d27ec07fe534ac32f3b251e4fc44b3cbfd9e09609ef4"},
+    {file = "ruff-0.3.4-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:6fc14fa742e1d8f24910e1fff0bd5e26d395b0e0e04cc1b15c7c5e5fe5b4af91"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d3ee7880f653cc03749a3bfea720cf2a192e4f884925b0cf7eecce82f0ce5854"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cf133dd744f2470b347f602452a88e70dadfbe0fcfb5fd46e093d55da65f82f7"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3f3860057590e810c7ffea75669bdc6927bfd91e29b4baa9258fd48b540a4365"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:986f2377f7cf12efac1f515fc1a5b753c000ed1e0a6de96747cdf2da20a1b369"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4fd98e85869603e65f554fdc5cddf0712e352fe6e61d29d5a6fe087ec82b76c"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:64abeed785dad51801b423fa51840b1764b35d6c461ea8caef9cf9e5e5ab34d9"},
+    {file = "ruff-0.3.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df52972138318bc7546d92348a1ee58449bc3f9eaf0db278906eb511889c4b50"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:98e98300056445ba2cc27d0b325fd044dc17fcc38e4e4d2c7711585bd0a958ed"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:519cf6a0ebed244dce1dc8aecd3dc99add7a2ee15bb68cf19588bb5bf58e0488"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_i686.whl", hash = "sha256:bb0acfb921030d00070539c038cd24bb1df73a2981e9f55942514af8b17be94e"},
+    {file = "ruff-0.3.4-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:cf187a7e7098233d0d0c71175375c5162f880126c4c716fa28a8ac418dcf3378"},
+    {file = "ruff-0.3.4-py3-none-win32.whl", hash = "sha256:af27ac187c0a331e8ef91d84bf1c3c6a5dea97e912a7560ac0cef25c526a4102"},
+    {file = "ruff-0.3.4-py3-none-win_amd64.whl", hash = "sha256:de0d5069b165e5a32b3c6ffbb81c350b1e3d3483347196ffdf86dc0ef9e37dd6"},
+    {file = "ruff-0.3.4-py3-none-win_arm64.whl", hash = "sha256:6810563cc08ad0096b57c717bd78aeac888a1bfd38654d9113cb3dc4d3f74232"},
+    {file = "ruff-0.3.4.tar.gz", hash = "sha256:f0f4484c6541a99862b693e13a151435a279b271cff20e37101116a21e2a1ad1"},
 ]
 
 [[package]]
 name = "s3transfer"
-version = "0.10.0"
+version = "0.10.1"
 requires_python = ">= 3.8"
 summary = "An Amazon S3 Transfer Manager"
 groups = ["default"]
@@ -606,8 +882,19 @@ dependencies = [
     "botocore<2.0a.0,>=1.33.2",
 ]
 files = [
-    {file = "s3transfer-0.10.0-py3-none-any.whl", hash = "sha256:3cdb40f5cfa6966e812209d0994f2a4709b561c88e90cf00c2696d2df4e56b2e"},
-    {file = "s3transfer-0.10.0.tar.gz", hash = "sha256:d0c8bbf672d5eebbe4e57945e23b972d963f07d82f661cabf678a5c88831595b"},
+    {file = "s3transfer-0.10.1-py3-none-any.whl", hash = "sha256:ceb252b11bcf87080fb7850a224fb6e05c8a776bab8f2b64b7f25b969464839d"},
+    {file = "s3transfer-0.10.1.tar.gz", hash = "sha256:5683916b4c724f799e600f41dd9e10a9ff19871bf87623cc8f491cb4f5fa0a19"},
+]
+
+[[package]]
+name = "setuptools"
+version = "69.2.0"
+requires_python = ">=3.8"
+summary = "Easily download, build, install, upgrade, and uninstall Python packages"
+groups = ["default"]
+files = [
+    {file = "setuptools-69.2.0-py3-none-any.whl", hash = "sha256:c21c49fb1042386df081cb5d86759792ab89efca84cf114889191cd09aacc80c"},
+    {file = "setuptools-69.2.0.tar.gz", hash = "sha256:0ff4183f8f42cd8fa3acea16c45205521a4ef28f73c6391d8a25e92893134f2e"},
 ]
 
 [[package]]
@@ -621,6 +908,17 @@ files = [
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
 ]
 
+[[package]]
+name = "smart-open"
+version = "6.4.0"
+requires_python = ">=3.6,<4.0"
+summary = "Utils for streaming large files (S3, HDFS, GCS, Azure Blob Storage, gzip, bz2...)"
+groups = ["default"]
+files = [
+    {file = "smart_open-6.4.0-py3-none-any.whl", hash = "sha256:8d3ef7e6997e8e42dd55c74166ed21e6ac70664caa32dd940b26d54a8f6b4142"},
+    {file = "smart_open-6.4.0.tar.gz", hash = "sha256:be3c92c246fbe80ebce8fbacb180494a481a77fcdcb7c1aadb2ea5b9c2bee8b9"},
+]
+
 [[package]]
 name = "soupsieve"
 version = "2.5"
@@ -632,15 +930,150 @@ files = [
     {file = "soupsieve-2.5.tar.gz", hash = "sha256:5663d5a7b3bfaeee0bc4372e7fc48f9cff4940b3eec54a6451cc5299f1097690"},
 ]
 
+[[package]]
+name = "spacy"
+version = "3.7.4"
+requires_python = ">=3.7"
+summary = "Industrial-strength Natural Language Processing (NLP) in Python"
+groups = ["default"]
+dependencies = [
+    "catalogue<2.1.0,>=2.0.6",
+    "cymem<2.1.0,>=2.0.2",
+    "jinja2",
+    "langcodes<4.0.0,>=3.2.0",
+    "murmurhash<1.1.0,>=0.28.0",
+    "numpy>=1.19.0; python_version >= \"3.9\"",
+    "packaging>=20.0",
+    "preshed<3.1.0,>=3.0.2",
+    "pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4",
+    "requests<3.0.0,>=2.13.0",
+    "setuptools",
+    "smart-open<7.0.0,>=5.2.1",
+    "spacy-legacy<3.1.0,>=3.0.11",
+    "spacy-loggers<2.0.0,>=1.0.0",
+    "srsly<3.0.0,>=2.4.3",
+    "thinc<8.3.0,>=8.2.2",
+    "tqdm<5.0.0,>=4.38.0",
+    "typer<0.10.0,>=0.3.0",
+    "wasabi<1.2.0,>=0.9.1",
+    "weasel<0.4.0,>=0.1.0",
+]
+files = [
+    {file = "spacy-3.7.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e82b9da21853d4aee46811804dc7e136895f087fda25c7585172d95eb9b70833"},
+    {file = "spacy-3.7.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:07ffedf51899441070fb70432f8f873696f39e0e31c9ce7403101c459f8a1281"},
+    {file = "spacy-3.7.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba57bcc111eca7b086ee33a9636df775cfd4b14302f7d0ffbc11e95ac0fb3f0e"},
+    {file = "spacy-3.7.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7580d1565f4d1ccbee9a18531f993a5b9b37ced96f145153dd4e98ceec607a55"},
+    {file = "spacy-3.7.4-cp311-cp311-win_amd64.whl", hash = "sha256:df99c6f0085b1ec8e88beb5fd96d4371cef6fc19c202c41fc4fadc2afd55a157"},
+    {file = "spacy-3.7.4.tar.gz", hash = "sha256:525f2ced2e40761562c8cace93ef6a1e6e8c483f27bd564bc1b15f608efbe85b"},
+]
+
+[[package]]
+name = "spacy-legacy"
+version = "3.0.12"
+requires_python = ">=3.6"
+summary = "Legacy registered functions for spaCy backwards compatibility"
+groups = ["default"]
+files = [
+    {file = "spacy-legacy-3.0.12.tar.gz", hash = "sha256:b37d6e0c9b6e1d7ca1cf5bc7152ab64a4c4671f59c85adaf7a3fcb870357a774"},
+    {file = "spacy_legacy-3.0.12-py2.py3-none-any.whl", hash = "sha256:476e3bd0d05f8c339ed60f40986c07387c0a71479245d6d0f4298dbd52cda55f"},
+]
+
+[[package]]
+name = "spacy-loggers"
+version = "1.0.5"
+requires_python = ">=3.6"
+summary = "Logging utilities for SpaCy"
+groups = ["default"]
+files = [
+    {file = "spacy-loggers-1.0.5.tar.gz", hash = "sha256:d60b0bdbf915a60e516cc2e653baeff946f0cfc461b452d11a4d5458c6fe5f24"},
+    {file = "spacy_loggers-1.0.5-py3-none-any.whl", hash = "sha256:196284c9c446cc0cdb944005384270d775fdeaf4f494d8e269466cfa497ef645"},
+]
+
+[[package]]
+name = "srsly"
+version = "2.4.8"
+requires_python = ">=3.6"
+summary = "Modern high-performance serialization utilities for Python"
+groups = ["default"]
+dependencies = [
+    "catalogue<2.1.0,>=2.0.3",
+]
+files = [
+    {file = "srsly-2.4.8-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5472ed9f581e10c32e79424c996cf54c46c42237759f4224806a0cd4bb770993"},
+    {file = "srsly-2.4.8-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:50f10afe9230072c5aad9f6636115ea99b32c102f4c61e8236d8642c73ec7a13"},
+    {file = "srsly-2.4.8-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c994a89ba247a4d4f63ef9fdefb93aa3e1f98740e4800d5351ebd56992ac75e3"},
+    {file = "srsly-2.4.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ace7ed4a0c20fa54d90032be32f9c656b6d75445168da78d14fe9080a0c208ad"},
+    {file = "srsly-2.4.8-cp311-cp311-win_amd64.whl", hash = "sha256:7a919236a090fb93081fbd1cec030f675910f3863825b34a9afbcae71f643127"},
+    {file = "srsly-2.4.8.tar.gz", hash = "sha256:b24d95a65009c2447e0b49cda043ac53fecf4f09e358d87a57446458f91b8a91"},
+]
+
+[[package]]
+name = "thinc"
+version = "8.2.3"
+requires_python = ">=3.6"
+summary = "A refreshing functional take on deep learning, compatible with your favorite libraries"
+groups = ["default"]
+dependencies = [
+    "blis<0.8.0,>=0.7.8",
+    "catalogue<2.1.0,>=2.0.4",
+    "confection<1.0.0,>=0.0.1",
+    "cymem<2.1.0,>=2.0.2",
+    "murmurhash<1.1.0,>=1.0.2",
+    "numpy>=1.19.0; python_version >= \"3.9\"",
+    "packaging>=20.0",
+    "preshed<3.1.0,>=3.0.2",
+    "pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4",
+    "setuptools",
+    "srsly<3.0.0,>=2.4.0",
+    "wasabi<1.2.0,>=0.8.1",
+]
+files = [
+    {file = "thinc-8.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9db67f460dae2e3aada1ff166394ce13c2dabb4db93d6bd79cd256f5beab9599"},
+    {file = "thinc-8.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:0d57bdf43e0acd1406d681bf988179f677cf1b385c86f744bf314d827383ce31"},
+    {file = "thinc-8.2.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:78311a593b8bf3f03af52bf71d6b364463c598f3540ea8387c00017d2a0e0a5d"},
+    {file = "thinc-8.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b9489ae7fec427064a50a0c3e7c661a95251756032e31316add2c8c13f98f93c"},
+    {file = "thinc-8.2.3-cp311-cp311-win_amd64.whl", hash = "sha256:d0bf3840d434e3dbdf294643e6d54d2042d0e652abc68dee16673f28269fc456"},
+    {file = "thinc-8.2.3.tar.gz", hash = "sha256:f5afc5222912a80bda8bdcec958362a2ba538d7027dc8db6154845d2859dca76"},
+]
+
+[[package]]
+name = "tqdm"
+version = "4.66.2"
+requires_python = ">=3.7"
+summary = "Fast, Extensible Progress Meter"
+groups = ["default"]
+dependencies = [
+    "colorama; platform_system == \"Windows\"",
+]
+files = [
+    {file = "tqdm-4.66.2-py3-none-any.whl", hash = "sha256:1ee4f8a893eb9bef51c6e35730cebf234d5d0b6bd112b0271e10ed7c24a02bd9"},
+    {file = "tqdm-4.66.2.tar.gz", hash = "sha256:6cd52cdf0fef0e0f543299cfc96fec90d7b8a7e88745f411ec33eb44d5ed3531"},
+]
+
+[[package]]
+name = "typer"
+version = "0.9.0"
+requires_python = ">=3.6"
+summary = "Typer, build great CLIs. Easy to code. Based on Python type hints."
+groups = ["default"]
+dependencies = [
+    "click<9.0.0,>=7.1.1",
+    "typing-extensions>=3.7.4.3",
+]
+files = [
+    {file = "typer-0.9.0-py3-none-any.whl", hash = "sha256:5d96d986a21493606a358cae4461bd8cdf83cbf33a5aa950ae629ca3b51467ee"},
+    {file = "typer-0.9.0.tar.gz", hash = "sha256:50922fd79aea2f4751a8e0408ff10d2662bd0c8bbfa84755a699f3bada2978b2"},
+]
+
 [[package]]
 name = "typing-extensions"
-version = "4.9.0"
+version = "4.10.0"
 requires_python = ">=3.8"
 summary = "Backported and Experimental Type Hints for Python 3.8+"
 groups = ["default"]
 files = [
-    {file = "typing_extensions-4.9.0-py3-none-any.whl", hash = "sha256:af72aea155e91adfc61c3ae9e0e342dbc0cba726d6cba4b6c72c1f34e47291cd"},
-    {file = "typing_extensions-4.9.0.tar.gz", hash = "sha256:23478f88c37f27d76ac8aee6c905017a143b0b1b886c3c9f66bc2fd94f9f5783"},
+    {file = "typing_extensions-4.10.0-py3-none-any.whl", hash = "sha256:69b1a937c3a517342112fb4c6df7e72fc39a38e7891a5730ed4985b5214b5475"},
+    {file = "typing_extensions-4.10.0.tar.gz", hash = "sha256:b0abd7c89e8fb96f98db18d86106ff1d90ab692004eb746cf6eda2682f91b3cb"},
 ]
 
 [[package]]
@@ -668,6 +1101,42 @@ files = [
     {file = "urllib3-2.0.7.tar.gz", hash = "sha256:c97dfde1f7bd43a71c8d2a58e369e9b2bf692d1334ea9f9cae55add7d0dd0f84"},
 ]
 
+[[package]]
+name = "wasabi"
+version = "1.1.2"
+requires_python = ">=3.6"
+summary = "A lightweight console printing and formatting toolkit"
+groups = ["default"]
+dependencies = [
+    "colorama>=0.4.6; sys_platform == \"win32\" and python_version >= \"3.7\"",
+]
+files = [
+    {file = "wasabi-1.1.2-py3-none-any.whl", hash = "sha256:0a3f933c4bf0ed3f93071132c1b87549733256d6c8de6473c5f7ed2e171b5cf9"},
+    {file = "wasabi-1.1.2.tar.gz", hash = "sha256:1aaef3aceaa32edb9c91330d29d3936c0c39fdb965743549c173cb54b16c30b5"},
+]
+
+[[package]]
+name = "weasel"
+version = "0.3.4"
+requires_python = ">=3.6"
+summary = "Weasel: A small and easy workflow system"
+groups = ["default"]
+dependencies = [
+    "cloudpathlib<0.17.0,>=0.7.0",
+    "confection<0.2.0,>=0.0.4",
+    "packaging>=20.0",
+    "pydantic!=1.8,!=1.8.1,<3.0.0,>=1.7.4",
+    "requests<3.0.0,>=2.13.0",
+    "smart-open<7.0.0,>=5.2.1",
+    "srsly<3.0.0,>=2.4.3",
+    "typer<0.10.0,>=0.3.0",
+    "wasabi<1.2.0,>=0.9.1",
+]
+files = [
+    {file = "weasel-0.3.4-py3-none-any.whl", hash = "sha256:ee48a944f051d007201c2ea1661d0c41035028c5d5a8bcb29a0b10f1100206ae"},
+    {file = "weasel-0.3.4.tar.gz", hash = "sha256:eb16f92dc9f1a3ffa89c165e3a9acd28018ebb656e0da4da02c0d7d8ae3f6178"},
+]
+
 [[package]]
 name = "win32-setctime"
 version = "1.1.0"

pyproject.toml

@@ -18,6 +18,8 @@ dependencies = [
     "aiolimiter>=1.1.0",
     "yarl>=1.9.4",
     "loguru>=0.7.2",
+    "spacy>=3.7.4",
+    "fr-core-news-sm @ https://github.com/explosion/spacy-models/releases/download/fr_core_news_sm-3.7.0/fr_core_news_sm-3.7.0.tar.gz",
 ]
 requires-python = "==3.11.*"
 readme = "README.md"

src/de_quoi_parle_le_monde/main.py

@@ -10,6 +10,7 @@ from de_quoi_parle_le_monde.internet_archive import (
     SnapshotNotYetAvailable,
 )
 from de_quoi_parle_le_monde.medias import media_collection
+from de_quoi_parle_le_monde.nlp import NlpService
 from de_quoi_parle_le_monde.storage import Storage
 
 
@@ -94,6 +95,7 @@ class ArchiveDownloader:
 
 async def main():
     http_client = HttpClient()
+    nlp = NlpService()
     storage = await Storage.create()
     dts = ArchiveDownloader.last_n_days_at_hours(10, [18])
 

src/de_quoi_parle_le_monde/nlp.py

@@ -0,0 +1,22 @@
+import spacy
+from attrs import frozen
+import cattrs
+
+
+@frozen
+class NlpEntity:
+    text: str
+    label: str
+
+
+class NlpService:
+    def __init__(self):
+        self.nlp = spacy.load("fr_core_news_sm")
+
+    def extract_entities(self, doc: str) -> list[NlpEntity]:
+        data = self.nlp(doc)
+        return [cattrs.structure({"text": e.text, "label": e.label_}) for e in data.ents]
+
+    def extract_lemmas(self, doc: str):
+        data = self.nlp(doc)
+        return [w.lemma_ for w in data if w.is_alpha and not w.is_stop]