update colab install & fix colab path

This commit is contained in:
yichuan520030910320
2025-07-26 18:07:31 -07:00
parent 73927b68ef
commit c87c0fe662
4 changed files with 143 additions and 8 deletions

View File

@@ -14,8 +14,8 @@
"outputs": [],
"source": [
"# install this if you are using colab\n",
"! pip install leann\n",
"\n",
"! uv pip install leann-core leann-backend-hnsw --no-deps\n",
"! uv pip install leann --no-deps\n",
"# For Colab environment, we need to set some environment variables\n",
"import os\n",
"os.environ['LEANN_LOG_LEVEL'] = 'INFO' # Enable more detailed logging"

View File

@@ -33,6 +33,13 @@ dependencies = [
"mlx-lm>=0.26.0; sys_platform == 'darwin'",
]
[project.optional-dependencies]
colab = [
"torch>=2.0.0,<3.0.0", # 限制torch版本避免冲突
"transformers>=4.30.0,<5.0.0", # 限制transformers版本
"accelerate>=0.20.0,<1.0.0", # 限制accelerate版本
]
[project.scripts]
leann = "leann.cli:main"

View File

@@ -117,8 +117,15 @@ class PassageManager:
assert source["type"] == "jsonl", "only jsonl is supported"
passage_file = source["path"]
index_file = source["index_path"] # .idx file
# Fix path resolution for Colab and other environments
if not Path(index_file).is_absolute():
# If relative path, try to resolve it properly
index_file = str(Path(index_file).resolve())
if not Path(index_file).exists():
raise FileNotFoundError(f"Passage index file not found: {index_file}")
with open(index_file, "rb") as f:
offset_map = pickle.load(f)
self.offset_maps[passage_file] = offset_map
@@ -381,6 +388,10 @@ class LeannBuilder:
class LeannSearcher:
def __init__(self, index_path: str, enable_warmup: bool = False, **backend_kwargs):
# Fix path resolution for Colab and other environments
if not Path(index_path).is_absolute():
index_path = str(Path(index_path).resolve())
self.meta_path_str = f"{index_path}.meta.json"
if not Path(self.meta_path_str).exists():
raise FileNotFoundError(

129
uv.lock generated
View File

@@ -701,6 +701,53 @@ toml = [
{ name = "tomli", marker = "python_full_version <= '3.11'" },
]
[[package]]
name = "cryptography"
version = "45.0.5"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "cffi", marker = "platform_python_implementation != 'PyPy'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/95/1e/49527ac611af559665f71cbb8f92b332b5ec9c6fbc4e88b0f8e92f5e85df/cryptography-45.0.5.tar.gz", hash = "sha256:72e76caa004ab63accdf26023fccd1d087f6d90ec6048ff33ad0445abf7f605a", size = 744903, upload-time = "2025-07-02T13:06:25.941Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/f0/fb/09e28bc0c46d2c547085e60897fea96310574c70fb21cd58a730a45f3403/cryptography-45.0.5-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:101ee65078f6dd3e5a028d4f19c07ffa4dd22cce6a20eaa160f8b5219911e7d8", size = 7043092, upload-time = "2025-07-02T13:05:01.514Z" },
{ url = "https://files.pythonhosted.org/packages/b1/05/2194432935e29b91fb649f6149c1a4f9e6d3d9fc880919f4ad1bcc22641e/cryptography-45.0.5-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3a264aae5f7fbb089dbc01e0242d3b67dffe3e6292e1f5182122bdf58e65215d", size = 4205926, upload-time = "2025-07-02T13:05:04.741Z" },
{ url = "https://files.pythonhosted.org/packages/07/8b/9ef5da82350175e32de245646b1884fc01124f53eb31164c77f95a08d682/cryptography-45.0.5-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e74d30ec9c7cb2f404af331d5b4099a9b322a8a6b25c4632755c8757345baac5", size = 4429235, upload-time = "2025-07-02T13:05:07.084Z" },
{ url = "https://files.pythonhosted.org/packages/7c/e1/c809f398adde1994ee53438912192d92a1d0fc0f2d7582659d9ef4c28b0c/cryptography-45.0.5-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3af26738f2db354aafe492fb3869e955b12b2ef2e16908c8b9cb928128d42c57", size = 4209785, upload-time = "2025-07-02T13:05:09.321Z" },
{ url = "https://files.pythonhosted.org/packages/d0/8b/07eb6bd5acff58406c5e806eff34a124936f41a4fb52909ffa4d00815f8c/cryptography-45.0.5-cp311-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:e6c00130ed423201c5bc5544c23359141660b07999ad82e34e7bb8f882bb78e0", size = 3893050, upload-time = "2025-07-02T13:05:11.069Z" },
{ url = "https://files.pythonhosted.org/packages/ec/ef/3333295ed58d900a13c92806b67e62f27876845a9a908c939f040887cca9/cryptography-45.0.5-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:dd420e577921c8c2d31289536c386aaa30140b473835e97f83bc71ea9d2baf2d", size = 4457379, upload-time = "2025-07-02T13:05:13.32Z" },
{ url = "https://files.pythonhosted.org/packages/d9/9d/44080674dee514dbb82b21d6fa5d1055368f208304e2ab1828d85c9de8f4/cryptography-45.0.5-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:d05a38884db2ba215218745f0781775806bde4f32e07b135348355fe8e4991d9", size = 4209355, upload-time = "2025-07-02T13:05:15.017Z" },
{ url = "https://files.pythonhosted.org/packages/c9/d8/0749f7d39f53f8258e5c18a93131919ac465ee1f9dccaf1b3f420235e0b5/cryptography-45.0.5-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:ad0caded895a00261a5b4aa9af828baede54638754b51955a0ac75576b831b27", size = 4456087, upload-time = "2025-07-02T13:05:16.945Z" },
{ url = "https://files.pythonhosted.org/packages/09/d7/92acac187387bf08902b0bf0699816f08553927bdd6ba3654da0010289b4/cryptography-45.0.5-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9024beb59aca9d31d36fcdc1604dd9bbeed0a55bface9f1908df19178e2f116e", size = 4332873, upload-time = "2025-07-02T13:05:18.743Z" },
{ url = "https://files.pythonhosted.org/packages/03/c2/840e0710da5106a7c3d4153c7215b2736151bba60bf4491bdb421df5056d/cryptography-45.0.5-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:91098f02ca81579c85f66df8a588c78f331ca19089763d733e34ad359f474174", size = 4564651, upload-time = "2025-07-02T13:05:21.382Z" },
{ url = "https://files.pythonhosted.org/packages/2e/92/cc723dd6d71e9747a887b94eb3827825c6c24b9e6ce2bb33b847d31d5eaa/cryptography-45.0.5-cp311-abi3-win32.whl", hash = "sha256:926c3ea71a6043921050eaa639137e13dbe7b4ab25800932a8498364fc1abec9", size = 2929050, upload-time = "2025-07-02T13:05:23.39Z" },
{ url = "https://files.pythonhosted.org/packages/1f/10/197da38a5911a48dd5389c043de4aec4b3c94cb836299b01253940788d78/cryptography-45.0.5-cp311-abi3-win_amd64.whl", hash = "sha256:b85980d1e345fe769cfc57c57db2b59cff5464ee0c045d52c0df087e926fbe63", size = 3403224, upload-time = "2025-07-02T13:05:25.202Z" },
{ url = "https://files.pythonhosted.org/packages/fe/2b/160ce8c2765e7a481ce57d55eba1546148583e7b6f85514472b1d151711d/cryptography-45.0.5-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:f3562c2f23c612f2e4a6964a61d942f891d29ee320edb62ff48ffb99f3de9ae8", size = 7017143, upload-time = "2025-07-02T13:05:27.229Z" },
{ url = "https://files.pythonhosted.org/packages/c2/e7/2187be2f871c0221a81f55ee3105d3cf3e273c0a0853651d7011eada0d7e/cryptography-45.0.5-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:3fcfbefc4a7f332dece7272a88e410f611e79458fab97b5efe14e54fe476f4fd", size = 4197780, upload-time = "2025-07-02T13:05:29.299Z" },
{ url = "https://files.pythonhosted.org/packages/b9/cf/84210c447c06104e6be9122661159ad4ce7a8190011669afceeaea150524/cryptography-45.0.5-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:460f8c39ba66af7db0545a8c6f2eabcbc5a5528fc1cf6c3fa9a1e44cec33385e", size = 4420091, upload-time = "2025-07-02T13:05:31.221Z" },
{ url = "https://files.pythonhosted.org/packages/3e/6a/cb8b5c8bb82fafffa23aeff8d3a39822593cee6e2f16c5ca5c2ecca344f7/cryptography-45.0.5-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:9b4cf6318915dccfe218e69bbec417fdd7c7185aa7aab139a2c0beb7468c89f0", size = 4198711, upload-time = "2025-07-02T13:05:33.062Z" },
{ url = "https://files.pythonhosted.org/packages/04/f7/36d2d69df69c94cbb2473871926daf0f01ad8e00fe3986ac3c1e8c4ca4b3/cryptography-45.0.5-cp37-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:2089cc8f70a6e454601525e5bf2779e665d7865af002a5dec8d14e561002e135", size = 3883299, upload-time = "2025-07-02T13:05:34.94Z" },
{ url = "https://files.pythonhosted.org/packages/82/c7/f0ea40f016de72f81288e9fe8d1f6748036cb5ba6118774317a3ffc6022d/cryptography-45.0.5-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:0027d566d65a38497bc37e0dd7c2f8ceda73597d2ac9ba93810204f56f52ebc7", size = 4450558, upload-time = "2025-07-02T13:05:37.288Z" },
{ url = "https://files.pythonhosted.org/packages/06/ae/94b504dc1a3cdf642d710407c62e86296f7da9e66f27ab12a1ee6fdf005b/cryptography-45.0.5-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:be97d3a19c16a9be00edf79dca949c8fa7eff621763666a145f9f9535a5d7f42", size = 4198020, upload-time = "2025-07-02T13:05:39.102Z" },
{ url = "https://files.pythonhosted.org/packages/05/2b/aaf0adb845d5dabb43480f18f7ca72e94f92c280aa983ddbd0bcd6ecd037/cryptography-45.0.5-cp37-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:7760c1c2e1a7084153a0f68fab76e754083b126a47d0117c9ed15e69e2103492", size = 4449759, upload-time = "2025-07-02T13:05:41.398Z" },
{ url = "https://files.pythonhosted.org/packages/91/e4/f17e02066de63e0100a3a01b56f8f1016973a1d67551beaf585157a86b3f/cryptography-45.0.5-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:6ff8728d8d890b3dda5765276d1bc6fb099252915a2cd3aff960c4c195745dd0", size = 4319991, upload-time = "2025-07-02T13:05:43.64Z" },
{ url = "https://files.pythonhosted.org/packages/f2/2e/e2dbd629481b499b14516eed933f3276eb3239f7cee2dcfa4ee6b44d4711/cryptography-45.0.5-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:7259038202a47fdecee7e62e0fd0b0738b6daa335354396c6ddebdbe1206af2a", size = 4554189, upload-time = "2025-07-02T13:05:46.045Z" },
{ url = "https://files.pythonhosted.org/packages/f8/ea/a78a0c38f4c8736287b71c2ea3799d173d5ce778c7d6e3c163a95a05ad2a/cryptography-45.0.5-cp37-abi3-win32.whl", hash = "sha256:1e1da5accc0c750056c556a93c3e9cb828970206c68867712ca5805e46dc806f", size = 2911769, upload-time = "2025-07-02T13:05:48.329Z" },
{ url = "https://files.pythonhosted.org/packages/79/b3/28ac139109d9005ad3f6b6f8976ffede6706a6478e21c889ce36c840918e/cryptography-45.0.5-cp37-abi3-win_amd64.whl", hash = "sha256:90cb0a7bb35959f37e23303b7eed0a32280510030daba3f7fdfbb65defde6a97", size = 3390016, upload-time = "2025-07-02T13:05:50.811Z" },
{ url = "https://files.pythonhosted.org/packages/f8/8b/34394337abe4566848a2bd49b26bcd4b07fd466afd3e8cce4cb79a390869/cryptography-45.0.5-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:206210d03c1193f4e1ff681d22885181d47efa1ab3018766a7b32a7b3d6e6afd", size = 3575762, upload-time = "2025-07-02T13:05:53.166Z" },
{ url = "https://files.pythonhosted.org/packages/8b/5d/a19441c1e89afb0f173ac13178606ca6fab0d3bd3ebc29e9ed1318b507fc/cryptography-45.0.5-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c648025b6840fe62e57107e0a25f604db740e728bd67da4f6f060f03017d5097", size = 4140906, upload-time = "2025-07-02T13:05:55.914Z" },
{ url = "https://files.pythonhosted.org/packages/4b/db/daceb259982a3c2da4e619f45b5bfdec0e922a23de213b2636e78ef0919b/cryptography-45.0.5-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:b8fa8b0a35a9982a3c60ec79905ba5bb090fc0b9addcfd3dc2dd04267e45f25e", size = 4374411, upload-time = "2025-07-02T13:05:57.814Z" },
{ url = "https://files.pythonhosted.org/packages/6a/35/5d06ad06402fc522c8bf7eab73422d05e789b4e38fe3206a85e3d6966c11/cryptography-45.0.5-pp310-pypy310_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:14d96584701a887763384f3c47f0ca7c1cce322aa1c31172680eb596b890ec30", size = 4140942, upload-time = "2025-07-02T13:06:00.137Z" },
{ url = "https://files.pythonhosted.org/packages/65/79/020a5413347e44c382ef1f7f7e7a66817cd6273e3e6b5a72d18177b08b2f/cryptography-45.0.5-pp310-pypy310_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:57c816dfbd1659a367831baca4b775b2a5b43c003daf52e9d57e1d30bc2e1b0e", size = 4374079, upload-time = "2025-07-02T13:06:02.043Z" },
{ url = "https://files.pythonhosted.org/packages/9b/c5/c0e07d84a9a2a8a0ed4f865e58f37c71af3eab7d5e094ff1b21f3f3af3bc/cryptography-45.0.5-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:b9e38e0a83cd51e07f5a48ff9691cae95a79bea28fe4ded168a8e5c6c77e819d", size = 3321362, upload-time = "2025-07-02T13:06:04.463Z" },
{ url = "https://files.pythonhosted.org/packages/c0/71/9bdbcfd58d6ff5084687fe722c58ac718ebedbc98b9f8f93781354e6d286/cryptography-45.0.5-pp311-pypy311_pp73-macosx_10_9_x86_64.whl", hash = "sha256:8c4a6ff8a30e9e3d38ac0539e9a9e02540ab3f827a3394f8852432f6b0ea152e", size = 3587878, upload-time = "2025-07-02T13:06:06.339Z" },
{ url = "https://files.pythonhosted.org/packages/f0/63/83516cfb87f4a8756eaa4203f93b283fda23d210fc14e1e594bd5f20edb6/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:bd4c45986472694e5121084c6ebbd112aa919a25e783b87eb95953c9573906d6", size = 4152447, upload-time = "2025-07-02T13:06:08.345Z" },
{ url = "https://files.pythonhosted.org/packages/22/11/d2823d2a5a0bd5802b3565437add16f5c8ce1f0778bf3822f89ad2740a38/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:982518cd64c54fcada9d7e5cf28eabd3ee76bd03ab18e08a48cad7e8b6f31b18", size = 4386778, upload-time = "2025-07-02T13:06:10.263Z" },
{ url = "https://files.pythonhosted.org/packages/5f/38/6bf177ca6bce4fe14704ab3e93627c5b0ca05242261a2e43ef3168472540/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:12e55281d993a793b0e883066f590c1ae1e802e3acb67f8b442e721e475e6463", size = 4151627, upload-time = "2025-07-02T13:06:13.097Z" },
{ url = "https://files.pythonhosted.org/packages/38/6a/69fc67e5266bff68a91bcb81dff8fb0aba4d79a78521a08812048913e16f/cryptography-45.0.5-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:5aa1e32983d4443e310f726ee4b071ab7569f58eedfdd65e9675484a4eb67bd1", size = 4385593, upload-time = "2025-07-02T13:06:15.689Z" },
{ url = "https://files.pythonhosted.org/packages/f6/34/31a1604c9a9ade0fdab61eb48570e09a796f4d9836121266447b0eaf7feb/cryptography-45.0.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:e357286c1b76403dd384d938f93c46b2b058ed4dfcdce64a770f0537ed3feb6f", size = 3331106, upload-time = "2025-07-02T13:06:18.058Z" },
]
[[package]]
name = "cycler"
version = "0.12.1"
@@ -1800,7 +1847,7 @@ wheels = [
[[package]]
name = "leann-backend-diskann"
version = "0.1.11"
version = "0.1.12"
source = { editable = "packages/leann-backend-diskann" }
dependencies = [
{ name = "leann-core" },
@@ -1811,14 +1858,14 @@ dependencies = [
[package.metadata]
requires-dist = [
{ name = "leann-core", specifier = "==0.1.11" },
{ name = "leann-core", specifier = "==0.1.12" },
{ name = "numpy" },
{ name = "protobuf", specifier = ">=3.19.0" },
]
[[package]]
name = "leann-backend-hnsw"
version = "0.1.11"
version = "0.1.12"
source = { editable = "packages/leann-backend-hnsw" }
dependencies = [
{ name = "leann-core" },
@@ -1830,7 +1877,7 @@ dependencies = [
[package.metadata]
requires-dist = [
{ name = "leann-core", specifier = "==0.1.11" },
{ name = "leann-core", specifier = "==0.1.12" },
{ name = "msgpack", specifier = ">=1.0.0" },
{ name = "numpy" },
{ name = "pyzmq", specifier = ">=23.0.0" },
@@ -1838,7 +1885,7 @@ requires-dist = [
[[package]]
name = "leann-core"
version = "0.1.11"
version = "0.1.12"
source = { editable = "packages/leann-core" }
dependencies = [
{ name = "accelerate" },
@@ -1850,7 +1897,10 @@ dependencies = [
{ name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
{ name = "numpy", version = "2.3.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
{ name = "openai" },
{ name = "pdfplumber" },
{ name = "psutil" },
{ name = "pymupdf" },
{ name = "pypdf2" },
{ name = "python-dotenv" },
{ name = "pyzmq" },
{ name = "requests" },
@@ -1863,6 +1913,7 @@ dependencies = [
[package.metadata]
requires-dist = [
{ name = "accelerate", specifier = ">=0.20.0" },
{ name = "accelerate", marker = "extra == 'colab'", specifier = ">=0.20.0,<1.0.0" },
{ name = "huggingface-hub", specifier = ">=0.20.0" },
{ name = "llama-index-core", specifier = ">=0.12.0" },
{ name = "mlx", marker = "sys_platform == 'darwin'", specifier = ">=0.26.3" },
@@ -1870,15 +1921,21 @@ requires-dist = [
{ name = "msgpack", specifier = ">=1.0.0" },
{ name = "numpy", specifier = ">=1.20.0" },
{ name = "openai", specifier = ">=1.0.0" },
{ name = "pdfplumber", specifier = ">=0.10.0" },
{ name = "psutil", specifier = ">=5.8.0" },
{ name = "pymupdf", specifier = ">=1.23.0" },
{ name = "pypdf2", specifier = ">=3.0.0" },
{ name = "python-dotenv", specifier = ">=1.0.0" },
{ name = "pyzmq", specifier = ">=23.0.0" },
{ name = "requests", specifier = ">=2.25.0" },
{ name = "sentence-transformers", specifier = ">=2.2.0" },
{ name = "torch", specifier = ">=2.0.0" },
{ name = "torch", marker = "extra == 'colab'", specifier = ">=2.0.0,<3.0.0" },
{ name = "tqdm", specifier = ">=4.60.0" },
{ name = "transformers", specifier = ">=4.30.0" },
{ name = "transformers", marker = "extra == 'colab'", specifier = ">=4.30.0,<5.0.0" },
]
provides-extras = ["colab"]
[[package]]
name = "leann-workspace"
@@ -1898,6 +1955,7 @@ dependencies = [
{ name = "llama-index-embeddings-huggingface" },
{ name = "llama-index-node-parser-docling" },
{ name = "llama-index-readers-docling" },
{ name = "llama-index-readers-file" },
{ name = "llama-index-vector-stores-faiss" },
{ name = "mlx", marker = "sys_platform == 'darwin'" },
{ name = "mlx-lm", marker = "sys_platform == 'darwin'" },
@@ -1906,9 +1964,12 @@ dependencies = [
{ name = "numpy", version = "2.3.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
{ name = "ollama" },
{ name = "openai" },
{ name = "pdfplumber" },
{ name = "protobuf" },
{ name = "psutil" },
{ name = "pymupdf" },
{ name = "pypdf2" },
{ name = "pypdfium2" },
{ name = "requests" },
{ name = "sentence-transformers" },
{ name = "sglang" },
@@ -1928,9 +1989,16 @@ dev = [
diskann = [
{ name = "leann-backend-diskann" },
]
documents = [
{ name = "beautifulsoup4" },
{ name = "openpyxl" },
{ name = "pandas" },
{ name = "python-docx" },
]
[package.metadata]
requires-dist = [
{ name = "beautifulsoup4", marker = "extra == 'documents'", specifier = ">=4.13.0" },
{ name = "black", marker = "extra == 'dev'", specifier = ">=23.0" },
{ name = "boto3" },
{ name = "colorama" },
@@ -1947,6 +2015,7 @@ requires-dist = [
{ name = "llama-index-embeddings-huggingface", specifier = ">=0.5.5" },
{ name = "llama-index-node-parser-docling" },
{ name = "llama-index-readers-docling" },
{ name = "llama-index-readers-file", specifier = ">=0.4.0" },
{ name = "llama-index-vector-stores-faiss", specifier = ">=0.4.0" },
{ name = "matplotlib", marker = "extra == 'dev'" },
{ name = "mlx", marker = "sys_platform == 'darwin'", specifier = ">=0.26.3" },
@@ -1955,11 +2024,17 @@ requires-dist = [
{ name = "numpy", specifier = ">=1.26.0" },
{ name = "ollama" },
{ name = "openai", specifier = ">=1.0.0" },
{ name = "openpyxl", marker = "extra == 'documents'", specifier = ">=3.1.0" },
{ name = "pandas", marker = "extra == 'documents'", specifier = ">=2.2.0" },
{ name = "pdfplumber", specifier = ">=0.11.0" },
{ name = "protobuf", specifier = "==4.25.3" },
{ name = "psutil", specifier = ">=5.8.0" },
{ name = "pymupdf", specifier = ">=1.26.0" },
{ name = "pypdf2", specifier = ">=3.0.0" },
{ name = "pypdfium2", specifier = ">=4.30.0" },
{ name = "pytest", marker = "extra == 'dev'", specifier = ">=7.0" },
{ name = "pytest-cov", marker = "extra == 'dev'", specifier = ">=4.0" },
{ name = "python-docx", marker = "extra == 'documents'", specifier = ">=0.8.11" },
{ name = "requests", specifier = ">=2.25.0" },
{ name = "ruff", marker = "extra == 'dev'", specifier = ">=0.1.0" },
{ name = "sentence-transformers", specifier = ">=2.2.0" },
@@ -1967,7 +2042,7 @@ requires-dist = [
{ name = "torch" },
{ name = "tqdm" },
]
provides-extras = ["dev", "diskann"]
provides-extras = ["dev", "diskann", "documents"]
[[package]]
name = "llama-cloud"
@@ -3279,6 +3354,33 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/cc/20/ff623b09d963f88bfde16306a54e12ee5ea43e9b597108672ff3a408aad6/pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08", size = 31191, upload-time = "2023-12-10T22:30:43.14Z" },
]
[[package]]
name = "pdfminer-six"
version = "20250506"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "charset-normalizer" },
{ name = "cryptography" },
]
sdist = { url = "https://files.pythonhosted.org/packages/78/46/5223d613ac4963e1f7c07b2660fe0e9e770102ec6bda8c038400113fb215/pdfminer_six-20250506.tar.gz", hash = "sha256:b03cc8df09cf3c7aba8246deae52e0bca7ebb112a38895b5e1d4f5dd2b8ca2e7", size = 7387678, upload-time = "2025-05-06T16:17:00.787Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/73/16/7a432c0101fa87457e75cb12c879e1749c5870a786525e2e0f42871d6462/pdfminer_six-20250506-py3-none-any.whl", hash = "sha256:d81ad173f62e5f841b53a8ba63af1a4a355933cfc0ffabd608e568b9193909e3", size = 5620187, upload-time = "2025-05-06T16:16:58.669Z" },
]
[[package]]
name = "pdfplumber"
version = "0.11.7"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "pdfminer-six" },
{ name = "pillow" },
{ name = "pypdfium2" },
]
sdist = { url = "https://files.pythonhosted.org/packages/6d/0d/4135821aa7b1a0b77a29fac881ef0890b46b0b002290d04915ed7acc0043/pdfplumber-0.11.7.tar.gz", hash = "sha256:fa67773e5e599de1624255e9b75d1409297c5e1d7493b386ce63648637c67368", size = 115518, upload-time = "2025-06-12T11:30:49.864Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/db/e0/52b67d4f00e09e497aec4f71bc44d395605e8ebcea52543242ed34c25ef9/pdfplumber-0.11.7-py3-none-any.whl", hash = "sha256:edd2195cca68bd770da479cf528a737e362968ec2351e62a6c0b71ff612ac25e", size = 60029, upload-time = "2025-06-12T11:30:48.89Z" },
]
[[package]]
name = "pexpect"
version = "4.9.0"
@@ -3774,6 +3876,21 @@ version = "2.10"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/5d/ab/34ec41718af73c00119d0351b7a2531d2ebddb51833a36448fc7b862be60/pylatexenc-2.10.tar.gz", hash = "sha256:3dd8fd84eb46dc30bee1e23eaab8d8fb5a7f507347b23e5f38ad9675c84f40d3", size = 162597, upload-time = "2021-04-06T07:56:07.854Z" }
[[package]]
name = "pymupdf"
version = "1.26.3"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/6d/d4/70a265e4bcd43e97480ae62da69396ef4507c8f9cfd179005ee731c92a04/pymupdf-1.26.3.tar.gz", hash = "sha256:b7d2c3ffa9870e1e4416d18862f5ccd356af5fe337b4511093bbbce2ca73b7e5", size = 75990308, upload-time = "2025-07-02T21:34:22.243Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/70/d3/c7af70545cd3097a869fd635bb6222108d3a0fb28c0b8254754a126c4cbb/pymupdf-1.26.3-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:ded891963944e5f13b03b88f6d9e982e816a4ec8689fe360876eef000c161f2b", size = 23057205, upload-time = "2025-07-02T21:26:16.326Z" },
{ url = "https://files.pythonhosted.org/packages/04/3d/ec5b69bfeaa5deefa7141fc0b20d77bb20404507cf17196b4eb59f1f2977/pymupdf-1.26.3-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:436a33c738bb10eadf00395d18a6992b801ffb26521ee1f361ae786dd283327a", size = 22406630, upload-time = "2025-07-02T21:27:10.112Z" },
{ url = "https://files.pythonhosted.org/packages/fc/20/661d3894bb05ad75ed6ca103ee2c3fa44d88a458b5c8d4a946b9c0f2569b/pymupdf-1.26.3-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:a2d7a3cd442f12f05103cb3bb1415111517f0a97162547a3720f3bbbc5e0b51c", size = 23450287, upload-time = "2025-07-03T07:22:19.317Z" },
{ url = "https://files.pythonhosted.org/packages/9c/7f/21828f018e65b16a033731d21f7b46d93fa81c6e8257f769ca4a1c2a1cb0/pymupdf-1.26.3-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:454f38c8cf07eb333eb4646dca10517b6e90f57ce2daa2265a78064109d85555", size = 24057319, upload-time = "2025-07-02T21:28:26.697Z" },
{ url = "https://files.pythonhosted.org/packages/71/5d/e8f88cd5a45b8f5fa6590ce8cef3ce0fad30eac6aac8aea12406f95bee7d/pymupdf-1.26.3-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:759b75d2f710ff4edf8d097d2e98f60e9ecef47632cead6f949b3412facdb9f0", size = 24261350, upload-time = "2025-07-02T21:29:21.733Z" },
{ url = "https://files.pythonhosted.org/packages/82/22/ecc560e4f281b5dffafbf3a81f023d268b1746d028044f495115b74a2e70/pymupdf-1.26.3-cp39-abi3-win32.whl", hash = "sha256:a839ed44742faa1cd4956bb18068fe5aae435d67ce915e901318646c4e7bbea6", size = 17116371, upload-time = "2025-07-02T21:30:23.253Z" },
{ url = "https://files.pythonhosted.org/packages/4a/26/8c72973b8833a72785cedc3981eb59b8ac7075942718bbb7b69b352cdde4/pymupdf-1.26.3-cp39-abi3-win_amd64.whl", hash = "sha256:b4cd5124d05737944636cf45fc37ce5824f10e707b0342efe109c7b6bd37a9cc", size = 18735124, upload-time = "2025-07-02T21:31:10.992Z" },
]
[[package]]
name = "pyparsing"
version = "3.2.3"