[NOTICKET] add pyarrow

pyproject.toml

@@ -90,6 +90,7 @@ dependencies = [
     "pdf2image>=1.17.0",
     "pytesseract>=0.3.13",
     "pypdf2>=3.0.1",
+    "pyarrow>=24.0.0",
 ]
 
 [project.optional-dependencies]

uv.lock

@@ -47,6 +47,7 @@ dependencies = [
     { name = "prometheus-client" },
     { name = "psycopg", extra = ["binary", "pool"] },
     { name = "psycopg2" },
+    { name = "pyarrow" },
     { name = "pydantic" },
     { name = "pydantic-settings" },
     { name = "pymongo" },
@@ -127,6 +128,7 @@ requires-dist = [
     { name = "prometheus-client", specifier = "==0.21.1" },
     { name = "psycopg", extras = ["binary", "pool"], specifier = "==3.2.3" },
     { name = "psycopg2", specifier = ">=2.9.11" },
+    { name = "pyarrow", specifier = ">=24.0.0" },
     { name = "pydantic", specifier = "==2.10.3" },
     { name = "pydantic-settings", specifier = "==2.7.0" },
     { name = "pymongo", specifier = ">=4.14.0" },
@@ -2400,6 +2402,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b5/bf/635fbe5dd10ed200afbbfbe98f8602829252ca1cce81cc48fb25ed8dadc0/psycopg2-2.9.11-cp312-cp312-win_amd64.whl", hash = "sha256:e03e4a6dbe87ff81540b434f2e5dc2bddad10296db5eea7bdc995bf5f4162938", size = 2713969, upload-time = "2025-10-10T11:10:15.946Z" },
 ]
 
+[[package]]
+name = "pyarrow"
+version = "24.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/91/13/13e1069b351bdc3881266e11147ffccf687505dbb0ea74036237f5d454a5/pyarrow-24.0.0.tar.gz", hash = "sha256:85fe721a14dd823aca09127acbb06c3ca723efbd436c004f16bca601b04dcc83", size = 1180261, upload-time = "2026-04-21T10:51:25.837Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b4/a9/9686d9f07837f91f775e8932659192e02c74f9d8920524b480b85212cc68/pyarrow-24.0.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:6233c9ed9ab9d1db47de57d9753256d9dcffbf42db341576099f0fd9f6bf4810", size = 34981559, upload-time = "2026-04-21T10:47:22.17Z" },
+    { url = "https://files.pythonhosted.org/packages/80/b6/0ddf0e9b6ead3474ab087ae598c76b031fc45532bf6a63f3a553440fb258/pyarrow-24.0.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:f7616236ec1bc2b15bfdec22a71ab38851c86f8f05ff64f379e1278cf20c634a", size = 36663654, upload-time = "2026-04-21T10:47:28.315Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/3b/926382efe8ce27ba729071d3566ade6dfb86bdf112f366000196b2f5780a/pyarrow-24.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:1617043b99bd33e5318ae18eb2919af09c71322ef1ca46566cdafc6e6712fb66", size = 45679394, upload-time = "2026-04-21T10:47:34.821Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/7a/829f7d9dfd37c207206081d6dad474d81dde29952401f07f2ba507814818/pyarrow-24.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:6165461f55ef6314f026de6638d661188e3455d3ec49834556a0ebbdbace18bb", size = 48863122, upload-time = "2026-04-21T10:47:42.056Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/e8/f88ce625fe8babaae64e8db2d417c7653adb3019b08aae85c5ed787dc816/pyarrow-24.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:3b13dedfe76a0ad2d1d859b0811b53827a4e9d93a0bcb05cf59333ab4980cc7e", size = 49376032, upload-time = "2026-04-21T10:47:48.967Z" },
+    { url = "https://files.pythonhosted.org/packages/36/7a/82c363caa145fff88fb475da50d3bf52bb024f61917be5424c3392eaf878/pyarrow-24.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:25ea65d868eb04015cd18e6df2fbe98f07e5bda2abefabcb88fce39a947716f6", size = 51929490, upload-time = "2026-04-21T10:47:55.981Z" },
+    { url = "https://files.pythonhosted.org/packages/66/1c/e3e72c8014ad2743ca64a701652c733cc5cbcee15c0463a32a8c55518d9e/pyarrow-24.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:295f0a7f2e242dabd513737cf076007dc5b2d59237e3eca37b05c0c6446f3826", size = 27355660, upload-time = "2026-04-21T10:48:01.718Z" },
+]
+
 [[package]]
 name = "pyasn1"
 version = "0.6.3"