Initializing gh-pages branch

.gitattributes

@@ -0,0 +1 @@
+benchmarks/datasets/** filter=lfs diff=lfs merge=lfs -text

.github/dependabot.yml

@@ -0,0 +1,11 @@
+version: 2
+updates:
+- package-ecosystem: pip
+  directory: "/"
+  schedule:
+    interval: daily
+    time: "13:00"
+  groups:
+    python-packages:
+      patterns:
+        - "*"

.github/pull_request_template.md

@@ -0,0 +1,14 @@
+## This PR contains:
+- [ ] New features
+- [ ] Changes to dev-tools e.g. CI config / github tooling
+- [ ] Docs
+- [ ] Bug fixes
+- [ ] Code refactor
+
+### What is the current behavior? (You can also link to an open issue here)
+
+### What is the new behavior?
+
+### Does this PR introduce a breaking change? (What changes might users need to make in their application due to this PR?)
+
+### Other information:

.github/workflows/build.yml

@@ -0,0 +1,49 @@
+name: Build
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+      - "release/**"
+
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Lint and format with Ruff
+        uses: chartboost/ruff-action@v1
+
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11"]
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[dev]
+      - name: Test with pytest
+        run: |
+          pytest -rA -x --doctest-modules --color=yes --cov=inspect_ai
+
+  package:
+    name: Build & inspect the package.
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: hynek/build-and-inspect-python-package@v1

.github/workflows/docs.yml

@@ -0,0 +1,26 @@
+on:
+  workflow_dispatch:
+
+name: Quarto Publish
+
+jobs:
+  build-deploy:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Set up Quarto
+        uses: quarto-dev/quarto-actions/setup@v2
+        with:
+          tinytex: true
+
+      - name: Render and Publish
+        uses: quarto-dev/quarto-actions/publish@v2
+        with:
+          target: gh-pages
+          path: docs
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/pypi.yml

@@ -0,0 +1,46 @@
+name: Publish to PyPI
+
+on:
+  workflow_dispatch:
+    inputs:
+      publish-release:
+        description: "Production Release"
+        required: false
+        type: boolean
+        default: false
+
+jobs:
+  publish:
+    name: Publish
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+    permissions:
+      id-token: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+      - name: Install pypa/build
+        run: >-
+          python3 -m
+          pip install
+          build
+          --user
+      - name: Build
+        run: python -m build
+      - name: Clean Wheel
+        run: rm -rf dist/inspect*.whl
+      - name: Publish package distributions to TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        if: ${{ ! inputs.publish-release }}
+        with:
+          repository-url: https://test.pypi.org/legacy/
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        if: ${{ inputs.publish-release }}

.gitignore

@@ -0,0 +1,169 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+*.env
+
+# 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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+*.*workspace
+data/datasets/*/hidden
+logs/
+
+# JS
+node_modules/
+
+/.luarc.json

.pre-commit-config.yaml

@@ -0,0 +1,24 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+# This should be the _latest_ version of python supported by us
+default_language_version:
+  python: python3.11
+repos:
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.1.6
+  hooks:
+    # Run the linter.
+    - id: ruff
+      args: [ --fix ]
+    # Run the formatter.
+    - id: ruff-format
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-json
+      - id: check-yaml
+      - id: debug-statements
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: requirements-txt-fixer

.vscode/extensions.json

@@ -0,0 +1,7 @@
+{
+  "recommendations": [
+    "ms-python.python",
+    "charliermarsh.ruff",
+    "ms-python.mypy-type-checker"
+  ]
+}

.vscode/settings.json

@@ -0,0 +1,22 @@
+{
+  "editor.formatOnSave": true,
+  "mypy-type-checker.importStrategy": "fromEnvironment",
+  "[json]": {
+    "editor.wordWrap": "on"
+  },
+  "[markdown]": {
+    "editor.formatOnSave": false
+  },
+  "[quarto]": {
+    "editor.formatOnSave": false
+  },
+  "search.exclude": {
+    "logs/**": true
+  },
+  "python.testing.pytestArgs": [
+    "tests"
+  ],
+  "python.testing.unittestEnabled": false,
+  "python.testing.pytestEnabled": true,
+  "quarto.render.renderOnSave": true
+}

DESCRIPTION.md

@@ -0,0 +1 @@
+Language model evaluations