Add README, CI, and other boilerplate (#1)

Add python infra, CI, testing, etc.. Also a basic README.

.github/workflows/ci.yaml

@@ -0,0 +1,22 @@
+name: CI
+
+on: [push]
+
+jobs:
+  test-python:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up python ${{ matrix.python-version }}
+        run: make py-prep PY_VERSION=${{ matrix.python-version }}
+
+      - name: Run static analysis
+        run: make lint
+
+      - name: Run tests
+        run: make test

.gitignore

@@ -0,0 +1,137 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# python node packages
+python/package-lock.json
+python/package.json
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Editors
+.vscode/
+.helix
+.*swp
+
+# Misc
+.DS_Store
+
+# Python wheels
+*.whl

Makefile

@@ -0,0 +1,44 @@
+SHELL := /bin/bash
+PROJECT_NAME := airtrain
+PY_VERSION := "3.11"
+
+.PHONY: wheel
+wheel:
+	uvx pip wheel -w dist .
+
+.PHONY: test-release
+test-release: wheel
+	uvx twine check dist/*airtrain*.whl
+	uvx twine upload --repository testpypi dist/*airtrain*.whl
+
+.PHONY: release
+release: wheel
+	uvx twine check dist/*airtrain*.whl
+	uvx twine upload dist/*airtrain*.whl
+
+.PHONY: py-prep
+py-prep:
+	uv --version || curl -LsSf https://astral.sh/uv/install.sh | sh
+	rm -rf ".venv" || echo "No virtualenv yet"
+	uv venv --python $(PY_VERSION)
+	uv tool install --force ruff==0.6.1
+	uv add --editable .
+
+.PHONY: sync
+sync:
+	uv sync
+
+.PHONY: fix
+fix:
+	uvx ruff format
+	uvx ruff check --fix --show-fixes src/airtrain
+
+.PHONY: lint
+lint:
+	uvx ruff format --check src/airtrain
+	uvx ruff check --fix src/airtrain
+	uv run mypy --explicit-package-bases src/airtrain
+
+.PHONY: test
+test:
+	uv run pytest ./

README.md

@@ -0,0 +1,65 @@
+<div align="center">
+  <img src="images/airtrain-logo.png" alt="Airtrain Ai Logo" style="vertical-align: middle; display: inline-block;" width="100px">
+</div>
+
+<p align="center">
+  <a href="https://github.com/sematic-ai/py-airtrain/actions/workflows/ci.yaml?query=branch%3Amain+" target="_blank">
+    <img height="30px" src="https://github.com/sematic-ai/py-airtrain/actions/workflows/ci.yaml/badge.svg?branch=main" alt="CI status">
+  </a>
+  <a href="./LICENSE" target="_blank">
+    <img height="30px" src="https://img.shields.io/pypi/l/sematic?style=for-the-badge" alt="License">
+  </a>
+  <a href="https://airtrain.ai" target="_blank">
+    <img height="30px" src="https://img.shields.io/badge/Made_by-Airtrain_🚀-blue?style=for-the-badge&logo=none" alt="Made by Airtrain">
+  </a>
+  <a href="https://docs.python.org/3.8/" target="_blank">
+    <img height="30px" src="https://img.shields.io/badge/Python-3.8-blue?style=for-the-badge&logo=python" alt="Python Version">
+  </a>
+  <a href="https://docs.python.org/3.9/" target="_blank">
+    <img height="30px" src="https://img.shields.io/badge/Python-3.9-blue?style=for-the-badge&logo=python" alt="Python Version">
+  </a>
+  <a href="https://docs.python.org/3.10/" target="_blank">
+    <img height="30px" src="https://img.shields.io/badge/Python-3.10-blue?style=for-the-badge&logo=python" alt="Python Version">
+  </a>
+  <a href="https://docs.python.org/3.11/" target="_blank">
+    <img height="30px" src="https://img.shields.io/badge/Python-3.11-blue?style=for-the-badge&logo=python" alt="Python Version">
+  </a>
+  <a href="https://docs.python.org/3.12/" target="_blank">
+    <img height="30px" src="https://img.shields.io/badge/Python-3.12-blue?style=for-the-badge&logo=python" alt="Python Version">
+  </a>
+  <a href="https://github.com/sematic-ai/py-airtrain/actions/workflows/ci.yaml?query=branch%3Amain+" target="_blank">
+    <img height="30px" src="https://github.com/sematic-ai/py-airtrain/actions/workflows/ci.yaml/badge.svg?branch=main" alt="CI status">
+  </a>
+</p>
+
+
+# Airtrain SDK
+
+This repository holds the SDK for interacting with
+[Airtrain](https://www.airtrain.ai/),
+the tool for improving your AI apps, RAG pipelines, and models by curating
+high-quality training and eval datasets.
+
+## Usage
+
+Obtain your API key by going to your user settings on
+https://app.airtrain.ai .
+
+Then you may upload a new dataset as follows:
+
+```python
+import airtrain as at
+
+# Can also be set with the environment variable AIRTRAIN_API_KEY
+at.api_key = "sUpErSeCr3t"
+
+url = at.upload_from_dicts(
+    [
+        {"foo": "some text", "bar": "more text"},
+        {"foo": "even more text", "bar": "so much text"},
+    ]
+).url
+
+# You may view your dataset at this URL
+print(f"Dataset URL: {url}")
+```

pyproject.toml

@@ -0,0 +1,75 @@
+[project]
+name = "airtrain"
+description = "SDK for interacting with https://airtrain.ai"
+version = "0.0.1"
+requires-python = ">=3.8"
+authors = [
+  {email = "[email protected]"},
+]
+readme = "README.md"
+license = {file = "LICENSE"}
+dependencies = [
+  "httpx>=0.25.0",
+  "pyarrow>=13.0.0",
+
+  # pyarrow requires numpy. Numpy version support is a bit
+  # complicated and isn't handled well transiently. This makes
+  # sure we support the broadest numpy dependency set possible.
+  "numpy>=1.26.0; python_version >= '3.12'",
+  "numpy<=1.24.4; python_version == '3.8'",
+  "numpy>=1.19.3; python_version >= '3.9'",
+
+  "airtrain",
+]
+
+classifiers = [
+  "License :: OSI Approved :: Apache Software License",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+  "Typing :: Typed",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+]
+
+[tool.uv]
+dev-dependencies = [
+  "mypy==1.11.1",
+  "ruff-lsp==0.0.35",
+  "python-lsp-ruff>=2.2.2",
+  "python-lsp-server>=1.11.0",
+  "pytest==7.4.0",
+]
+
+[tool.uv.sources]
+airtrain = { workspace = true }
+
+[project.urls]
+Homepage = "https://airtrain.ai"
+Documentation = "https://docs.airtrain.ai/"
+
+[build-system]
+requires = ["setuptools", "setuptools-scm"]
+build-backend = "setuptools.build_meta"
+
+[tool.ruff]
+line-length = 90
+
+[tool.ruff.lint]
+select = ["E", "F", "I"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["airtrain"]
+
+# Use a single line after each import block.
+lines-after-imports = 2
+
+[tool.pylsp.plugins.ruff]
+enabled = true
+
+[[tool.mypy.overrides]]
+module = "airtrain.*"
+ignore_missing_imports = true

src/airtrain/__init__.py

@@ -0,0 +1 @@
+from airtrain.core import DatasetMetadata, upload_from_dicts  # noqa: F401

src/airtrain/core.py

@@ -0,0 +1,31 @@
+from dataclasses import dataclass, fields
+from typing import Any, Dict, Iterable, Union
+
+
+@dataclass
+class DatasetMetadata:
+    name: str
+    id: str
+    url: str
+    size: int
+
+    def __post_init__(self) -> None:
+        for field in fields(self):
+            value = getattr(self, field.name)
+            if not isinstance(value, field.type):
+                raise ValueError(
+                    f"Field '{field.name}' must be {field.type}. Got: '{value}'"
+                )
+
+
+def upload_from_dicts(
+    data: Iterable[Dict[str, Any]],
+    name: Union[str, None] = None,
+    embedding_column: Union[str, None] = None,
+) -> DatasetMetadata:
+    return DatasetMetadata(
+        name=name or "My Dataset",
+        id="abc123",
+        url="https://example.com",
+        size=0,
+    )

src/tests/test_core.py

@@ -0,0 +1,6 @@
+from airtrain.core import DatasetMetadata, upload_from_dicts
+
+
+def test_upload_from_dicts():
+    result = upload_from_dicts([{"foo": 42}, {"foo": 43}], name="Foo dataset")
+    assert isinstance(result, DatasetMetadata)