mirror of
https://github.com/lancedb/lancedb.git
synced 2025-12-27 07:09:57 +00:00
cc81f3e1a5
@wjones127 is there a standard way you guys setup your virtualenv? I can
either relist all the dependencies in the pyright precommit section, or
specify a venv, or the user has to be in the virtual environment when
they run git commit. If the venv location was standardized or a python
manager like `uv` was used it would be easier to avoid duplicating the
pyright dependency list.
Per your suggestion, in `pyproject.toml` I added in all the passing
files to the `includes` section.
For ruff I upgraded the version and removed "TCH" which doesn't exist as
an option.
I added a `pyright_report.csv` which contains a list of all files sorted
by pyright errors ascending as a todo list to work on.
I fixed about 30 issues in `table.py` stemming from str's being passed
into methods that required a string within a set of string Literals by
extracting them into `types.py`
Can you verify in the rust bridge that the schema should be a property
and not a method here? If it's a method, then there's another place in
the code where `inner.schema` should be `inner.schema()`
``` python
class RecordBatchStream:
@property
def schema(self) -> pa.Schema: ...
```
Also unless the `_lancedb.pyi` file is wrong, then there is no
`__anext__` here for `__inner` when it's not an `AsyncGenerator` and
only `next` is defined:
``` python
async def __anext__(self) -> pa.RecordBatch:
return await self._inner.__anext__()
if isinstance(self._inner, AsyncGenerator):
batch = await self._inner.__anext__()
else:
batch = await self._inner.next()
if batch is None:
raise StopAsyncIteration
return batch
```
in the else statement, `_inner` is a `RecordBatchStream`
```python
class RecordBatchStream:
@property
def schema(self) -> pa.Schema: ...
async def next(self) -> Optional[pa.RecordBatch]: ...
```
---------
Co-authored-by: Will Jones <willjones127@gmail.com>
131 lines
3.3 KiB
TOML
131 lines
3.3 KiB
TOML
[project]
|
|
name = "lancedb"
|
|
# version in Cargo.toml
|
|
dynamic = ["version"]
|
|
dependencies = [
|
|
"deprecation",
|
|
"tqdm>=4.27.0",
|
|
"pyarrow>=14",
|
|
"pydantic>=1.10",
|
|
"packaging",
|
|
"overrides>=0.7",
|
|
]
|
|
description = "lancedb"
|
|
authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
|
|
license = { file = "LICENSE" }
|
|
readme = "README.md"
|
|
requires-python = ">=3.9"
|
|
keywords = [
|
|
"data-format",
|
|
"data-science",
|
|
"machine-learning",
|
|
"arrow",
|
|
"data-analytics",
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 3 - Alpha",
|
|
"Environment :: Console",
|
|
"Intended Audience :: Science/Research",
|
|
"License :: OSI Approved :: Apache Software License",
|
|
"Operating System :: OS Independent",
|
|
"Programming Language :: Python",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3 :: Only",
|
|
"Programming Language :: Python :: 3.9",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Topic :: Scientific/Engineering",
|
|
]
|
|
|
|
[project.urls]
|
|
repository = "https://github.com/lancedb/lancedb"
|
|
|
|
[project.optional-dependencies]
|
|
tests = [
|
|
"aiohttp",
|
|
"boto3",
|
|
"pandas>=1.4",
|
|
"pytest",
|
|
"pytest-mock",
|
|
"pytest-asyncio",
|
|
"duckdb",
|
|
"pytz",
|
|
"polars>=0.19, <=1.3.0",
|
|
"tantivy",
|
|
"pyarrow-stubs",
|
|
"pylance~=0.23.2",
|
|
]
|
|
dev = [
|
|
"ruff",
|
|
"pre-commit",
|
|
"pyright",
|
|
'typing-extensions>=4.0.0; python_version < "3.11"',
|
|
]
|
|
docs = ["mkdocs", "mkdocs-jupyter", "mkdocs-material", "mkdocstrings[python]"]
|
|
clip = ["torch", "pillow", "open-clip"]
|
|
embeddings = [
|
|
"requests>=2.31.0",
|
|
"openai>=1.6.1",
|
|
"sentence-transformers",
|
|
"torch",
|
|
"pillow",
|
|
"open-clip-torch",
|
|
"cohere",
|
|
"huggingface_hub",
|
|
"InstructorEmbedding",
|
|
"google.generativeai",
|
|
"boto3>=1.28.57",
|
|
"awscli>=1.29.57",
|
|
"botocore>=1.31.57",
|
|
"ollama",
|
|
"ibm-watsonx-ai>=1.1.2",
|
|
]
|
|
azure = ["adlfs>=2024.2.0"]
|
|
|
|
[tool.maturin]
|
|
python-source = "python"
|
|
module-name = "lancedb._lancedb"
|
|
|
|
[build-system]
|
|
requires = ["maturin>=1.4"]
|
|
build-backend = "maturin"
|
|
|
|
[tool.ruff.lint]
|
|
select = ["F", "E", "W", "G", "PERF"]
|
|
|
|
[tool.pytest.ini_options]
|
|
addopts = "--strict-markers --ignore-glob=lancedb/embeddings/*.py"
|
|
markers = [
|
|
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
|
|
"asyncio",
|
|
"s3_test",
|
|
]
|
|
|
|
[tool.pyright]
|
|
include = [
|
|
"python/lancedb/index.py",
|
|
"python/lancedb/rerankers/util.py",
|
|
"python/lancedb/rerankers/__init__.py",
|
|
"python/lancedb/rerankers/voyageai.py",
|
|
"python/lancedb/rerankers/jinaai.py",
|
|
"python/lancedb/rerankers/openai.py",
|
|
"python/lancedb/rerankers/cross_encoder.py",
|
|
"python/lancedb/rerankers/colbert.py",
|
|
"python/lancedb/rerankers/answerdotai.py",
|
|
"python/lancedb/rerankers/cohere.py",
|
|
"python/lancedb/arrow.py",
|
|
"python/lancedb/__init__.py",
|
|
"python/lancedb/types.py",
|
|
"python/lancedb/integrations/__init__.py",
|
|
"python/lancedb/exceptions.py",
|
|
"python/lancedb/background_loop.py",
|
|
"python/lancedb/schema.py",
|
|
"python/lancedb/remote/__init__.py",
|
|
"python/lancedb/remote/errors.py",
|
|
"python/lancedb/embeddings/__init__.py",
|
|
"python/lancedb/_lancedb.pyi",
|
|
]
|
|
exclude = ["python/tests/"]
|
|
pythonVersion = "3.12"
|