feat: update dependencies in pyproject.toml and uv.lock

pyproject.toml

@@ -30,6 +30,7 @@ dev = [
     "beir>=2.2.0",
     "boto3>=1.42.58",
     "chonkie[elastic,semantic]>=1.6.0",
+    "coir-eval>=0.7.0",
     "evidently>=0.7.20",
     "flatbuffers>=25.12.19",
     "jupyter>=1.1.1",
@@ -44,4 +45,4 @@ dev = [
     "tree-sitter-language-pack>=0.13.0",
 ]
 [tool.pytest.ini_options]
-testpaths = ["Docker/tests"]
+testpaths = ["Docker/tests"]

uv.lock

@@ -127,6 +127,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b4/63/278a98c715ae467624eafe375542d8ba9b4383a016df8fdefe0ae28382a7/aiohttp-3.13.3-cp314-cp314t-win_amd64.whl", hash = "sha256:44531a36aa2264a1860089ffd4dce7baf875ee5a6079d5fb42e261c704ef7344", size = 499694, upload-time = "2026-01-03T17:32:24.546Z" },
 ]
 
+[[package]]
+name = "aiolimiter"
+version = "1.2.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f1/23/b52debf471f7a1e42e362d959a3982bdcb4fe13a5d46e63d28868807a79c/aiolimiter-1.2.1.tar.gz", hash = "sha256:e02a37ea1a855d9e832252a105420ad4d15011505512a1a1d814647451b5cca9", size = 7185, upload-time = "2024-12-08T15:31:51.496Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f3/ba/df6e8e1045aebc4778d19b8a3a9bc1808adb1619ba94ca354d9ba17d86c3/aiolimiter-1.2.1-py3-none-any.whl", hash = "sha256:d3f249e9059a20badcb56b61601a83556133655c11d1eb3dd3e04ff069e5f3c7", size = 6711, upload-time = "2024-12-08T15:31:49.874Z" },
+]
+
 [[package]]
 name = "aiosignal"
 version = "1.4.0"
@@ -275,6 +284,7 @@ dev = [
     { name = "beir" },
     { name = "boto3" },
     { name = "chonkie", extra = ["elastic", "semantic"] },
+    { name = "coir-eval" },
     { name = "evidently" },
     { name = "flatbuffers" },
     { name = "jupyter" },
@@ -316,6 +326,7 @@ dev = [
     { name = "beir", specifier = ">=2.2.0" },
     { name = "boto3", specifier = ">=1.42.58" },
     { name = "chonkie", extras = ["elastic", "semantic"], specifier = ">=1.6.0" },
+    { name = "coir-eval", specifier = ">=0.7.0" },
     { name = "evidently", specifier = ">=0.7.20" },
     { name = "flatbuffers", specifier = ">=25.12.19" },
     { name = "jupyter", specifier = ">=1.1.1" },
@@ -670,6 +681,29 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/98/78/01c019cdb5d6498122777c1a43056ebb3ebfeef2076d9d026bfe15583b2b/click-8.3.1-py3-none-any.whl", hash = "sha256:981153a64e25f12d547d3426c367a4857371575ee7ad18df2a6183ab0545b2a6", size = 108274, upload-time = "2025-11-15T20:45:41.139Z" },
 ]
 
+[[package]]
+name = "coir-eval"
+version = "0.7.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "datasets" },
+    { name = "faiss-cpu" },
+    { name = "numpy" },
+    { name = "pytrec-eval-terrier" },
+    { name = "requests" },
+    { name = "rich" },
+    { name = "scikit-learn" },
+    { name = "scipy" },
+    { name = "sentence-transformers" },
+    { name = "torch" },
+    { name = "tqdm" },
+    { name = "voyageai" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f2/eb/56f3e8307f9a407d43532611ce0fdbf8fe41030bca7ebf05dbb14df19bb2/coir_eval-0.7.0.tar.gz", hash = "sha256:3ddd86ce63bea9cd64fa6b3fc17e405b2adbcd29873e80977817a183bd7b0315", size = 40274, upload-time = "2024-07-02T11:29:46.339Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c7/ab/d4da1315873ac8fe9da39469db0c578f05a0e8f9ff22485d592622f3d28e/coir_eval-0.7.0-py3-none-any.whl", hash = "sha256:4d80b890b37d371da1413ae2462dd5684bfef516b2e09ec42da7c42f6219a4c1", size = 58457, upload-time = "2024-07-02T11:29:44.409Z" },
+]
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@@ -988,6 +1022,31 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c1/ea/53f2148663b321f21b5a606bd5f191517cf40b7072c0497d3c92c4a13b1e/executing-2.2.1-py2.py3-none-any.whl", hash = "sha256:760643d3452b4d777d295bb167ccc74c64a81df23fb5e08eff250c425a4b2017", size = 28317, upload-time = "2025-09-01T09:48:08.5Z" },
 ]
 
+[[package]]
+name = "faiss-cpu"
+version = "1.13.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+    { name = "packaging" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/c9/671f66f6b31ec48e5825d36435f0cb91189fa8bb6b50724029dbff4ca83c/faiss_cpu-1.13.2-cp310-abi3-macosx_14_0_arm64.whl", hash = "sha256:a9064eb34f8f64438dd5b95c8f03a780b1a3f0b99c46eeacb1f0b5d15fc02dc1", size = 3452776, upload-time = "2025-12-24T10:27:01.419Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/4a/97150aa1582fb9c2bca95bd8fc37f27d3b470acec6f0a6833844b21e4b40/faiss_cpu-1.13.2-cp310-abi3-macosx_14_0_x86_64.whl", hash = "sha256:c8d097884521e1ecaea6467aeebbf1aa56ee4a36350b48b2ca6b39366565c317", size = 7896434, upload-time = "2025-12-24T10:27:03.592Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/d0/0940575f059591ca31b63a881058adb16a387020af1709dcb7669460115c/faiss_cpu-1.13.2-cp310-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0ee330a284042c2480f2e90450a10378fd95655d62220159b1408f59ee83ebf1", size = 11485825, upload-time = "2025-12-24T10:27:05.681Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/e1/a5acac02aa593809f0123539afe7b4aff61d1db149e7093239888c9053e1/faiss_cpu-1.13.2-cp310-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ab88ee287c25a119213153d033f7dd64c3ccec466ace267395872f554b648cd7", size = 23845772, upload-time = "2025-12-24T10:27:08.194Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/7b/49dcaf354834ec457e85ca769d50bc9b5f3003fab7c94a9dcf08cf742793/faiss_cpu-1.13.2-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:85511129b34f890d19c98b82a0cd5ffb27d89d1cec2ee41d2621ee9f9ef8cf3f", size = 13477567, upload-time = "2025-12-24T10:27:10.822Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/6b/12bb4037921c38bb2c0b4cfc213ca7e04bbbebbfea89b0b5746248ce446e/faiss_cpu-1.13.2-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:8b32eb4065bac352b52a9f5ae07223567fab0a976c7d05017c01c45a1c24264f", size = 25102239, upload-time = "2025-12-24T10:27:13.476Z" },
+    { url = "https://files.pythonhosted.org/packages/14/6d/40439a05e4e60a0e889aa68b08ec70f5c8e32901f75f2be25c593a2e050e/faiss_cpu-1.13.2-cp311-cp311-win_amd64.whl", hash = "sha256:7c5944d7807d58fe7244b6aba06be710ee7ed99343365ed92699349efe979f51", size = 18879906, upload-time = "2025-12-24T10:27:19.041Z" },
+    { url = "https://files.pythonhosted.org/packages/9f/f9/b97eadbdd9e00f945d1566c7101382344f504596bfb19219465b0fc61e6e/faiss_cpu-1.13.2-cp311-cp311-win_arm64.whl", hash = "sha256:19508a1badfb36e456c1c8664eeb948349f604db5c7545f277a0126b4a84b080", size = 8548280, upload-time = "2025-12-24T10:27:22.114Z" },
+    { url = "https://files.pythonhosted.org/packages/87/ff/35ed875423200c17bdd594ce921abfc1812ddd21e09355290b9a94e170ab/faiss_cpu-1.13.2-cp312-cp312-win_amd64.whl", hash = "sha256:b82c01d30430dd7b1fa442001b9099735d1a82f6bb72033acdc9206d5ac66a64", size = 18890300, upload-time = "2025-12-24T10:27:24.194Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/3a/bbdf5deaf6feb34b46b469c0a0acd40216c3d3c6ecf5aeb71d56b8a650e3/faiss_cpu-1.13.2-cp312-cp312-win_arm64.whl", hash = "sha256:2c4f696ae76e7c97cbc12311db83aaf1e7f4f7be06a3ffea7e5b0e8ec1fd805b", size = 8553157, upload-time = "2025-12-24T10:27:26.38Z" },
+    { url = "https://files.pythonhosted.org/packages/60/4b/903d85bf3a8264d49964ec799e45c7ffc91098606b8bc9ef2c904c1a56cb/faiss_cpu-1.13.2-cp313-cp313-win_amd64.whl", hash = "sha256:cb4b5ee184816a4b099162ac93c0d7f0033d81a88e7c1291d0a9cc41ec348984", size = 18891330, upload-time = "2025-12-24T10:27:28.806Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/52/5d10642da628f63544aab27e48416be4a7ea25c6b81d8bd65016d8538b00/faiss_cpu-1.13.2-cp313-cp313-win_arm64.whl", hash = "sha256:1243967eeb2298791ff7f3683a4abd2100d7e6ec7542ca05c3b75d47a7f621e5", size = 8553088, upload-time = "2025-12-24T10:27:31.325Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/b1/daaab8046f56c60079648bd83774f61b283b59a9930a2f60790ee4cdedfe/faiss_cpu-1.13.2-cp314-cp314-win_amd64.whl", hash = "sha256:c8b645e7d56591aa35dc75415bb53a62e4a494dba010e16f4b67daeffd830bd7", size = 18892621, upload-time = "2025-12-24T10:27:33.923Z" },
+    { url = "https://files.pythonhosted.org/packages/06/6f/5eaf3e249c636e616ebb52e369a4a2f1d32b1caf9a611b4f917b3dd21423/faiss_cpu-1.13.2-cp314-cp314-win_arm64.whl", hash = "sha256:8113a2a80b59fe5653cf66f5c0f18be0a691825601a52a614c30beb1fca9bc7c", size = 8556374, upload-time = "2025-12-24T10:27:36.653Z" },
+]
+
 [[package]]
 name = "faker"
 version = "40.5.1"
@@ -1061,6 +1120,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/1f/f6/da4db31001e854025ffd26bc9ba0740a9cbba2c3259695f7c5834908b336/fastuuid-0.14.0-cp314-cp314-win_amd64.whl", hash = "sha256:df61342889d0f5e7a32f7284e55ef95103f2110fee433c2ae7c2c0956d76ac8a", size = 156457, upload-time = "2025-10-19T22:33:44.579Z" },
 ]
 
+[[package]]
+name = "ffmpeg-python"
+version = "0.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "future" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dd/5e/d5f9105d59c1325759d838af4e973695081fbbc97182baf73afc78dec266/ffmpeg-python-0.2.0.tar.gz", hash = "sha256:65225db34627c578ef0e11c8b1eb528bb35e024752f6f10b78c011f6f64c4127", size = 21543, upload-time = "2019-07-06T00:19:08.989Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d7/0c/56be52741f75bad4dc6555991fabd2e07b432d333da82c11ad701123888a/ffmpeg_python-0.2.0-py3-none-any.whl", hash = "sha256:ac441a0404e053f8b6a1113a77c0f452f1cfc62f6344a769475ffdc0f56c23c5", size = 25024, upload-time = "2019-07-06T00:19:07.215Z" },
+]
+
 [[package]]
 name = "filelock"
 version = "3.24.3"
@@ -1206,6 +1277,15 @@ http = [
     { name = "aiohttp" },
 ]
 
+[[package]]
+name = "future"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a7/b2/4140c69c6a66432916b26158687e821ba631a4c9273c474343badf84d3ba/future-1.0.0.tar.gz", hash = "sha256:bd2968309307861edae1458a4f8a4f3598c03be43b97521076aebf5d94c07b05", size = 1228490, upload-time = "2024-02-21T11:52:38.461Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/da/71/ae30dadffc90b9006d77af76b393cb9dfbfc9629f339fc1574a1c52e6806/future-1.0.0-py3-none-any.whl", hash = "sha256:929292d34f5872e70396626ef385ec22355a1fae8ad29e1a734c3e43f9fbc216", size = 491326, upload-time = "2024-02-21T11:52:35.956Z" },
+]
+
 [[package]]
 name = "greenlet"
 version = "3.3.2"
@@ -5712,6 +5792,27 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e4/16/c1fd27e9549f3c4baf1dc9c20c456cd2f822dbf8de9f463824b0c0357e06/uvloop-0.22.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6cde23eeda1a25c75b2e07d39970f3374105d5eafbaab2a4482be82f272d5a5e", size = 4296730, upload-time = "2025-10-16T22:17:00.744Z" },
 ]
 
+[[package]]
+name = "voyageai"
+version = "0.3.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "aiohttp" },
+    { name = "aiolimiter" },
+    { name = "ffmpeg-python" },
+    { name = "langchain-text-splitters" },
+    { name = "numpy", marker = "python_full_version < '3.14'" },
+    { name = "pillow" },
+    { name = "pydantic" },
+    { name = "requests" },
+    { name = "tenacity" },
+    { name = "tokenizers" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/94/16/1b46b3cd401e1717a68197c1fe336d7bb4e0a1833f8105e1738f5b1add05/voyageai-0.3.7.tar.gz", hash = "sha256:826cd97f97223f42b5babc5c459c9c80f3a8215ce5c0e007b0b276550f790d24", size = 26485, upload-time = "2025-12-16T18:43:05.26Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/60/64/89f6325666d6836979f94ac88b96fefc7527e02e61abc81359843585e088/voyageai-0.3.7-py3-none-any.whl", hash = "sha256:909f6c033001e5a3b3caf970525bf3614a1bfef9003cf3c3b68207dfdb53e86d", size = 34691, upload-time = "2025-12-16T18:43:04.073Z" },
+]
+
 [[package]]
 name = "watchdog"
 version = "6.0.0"