chore: upgrade scaffolding (#105)

Author: lsorber

.copier-answers.yml

@@ -1,8 +1,9 @@
-_commit: v1.2.0
+_commit: v1.5.1
 _src_path: gh:superlinear-ai/substrate
 author_email: laurent@superlinear.eu
 author_name: Laurent Sorber
-project_description: A Python toolkit for Retrieval-Augmented Generation (RAG) with SQLite or PostgreSQL.
+project_description: A Python toolkit for Retrieval-Augmented Generation (RAG) with
+    SQLite or PostgreSQL.
 project_name: raglite
 project_type: package
 project_url: https://github.com/superlinear-ai/raglite

.devcontainer/devcontainer.json

@@ -8,7 +8,7 @@
     },
     "overrideCommand": true,
     "remoteUser": "user",
-    "postStartCommand": "sudo chown -R user:user /opt/ && uv sync --python ${PYTHON_VERSION:-3.10} ${RESOLUTION_STRATEGY:+--resolution $RESOLUTION_STRATEGY} --all-extras && pre-commit install --install-hooks",
+    "postStartCommand": "sudo chown -R user:user /opt/ && uv sync --python ${localEnv:PYTHON_VERSION:3.10} --resolution ${localEnv:RESOLUTION_STRATEGY:highest} --all-extras && pre-commit install --install-hooks",
     "customizations": {
         "jetbrains": {
             "backend": "PyCharm",
@@ -51,7 +51,7 @@
                 ],
                 "files.autoSave": "onFocusChange",
                 "github.copilot.chat.agent.enabled": true,
-                "github.copilot.chat.edits.codesearch.enabled": true,
+                "github.copilot.chat.codesearch.enabled": true,
                 "github.copilot.chat.edits.enabled": true,
                 "github.copilot.nextEditSuggestions.enabled": true,
                 "jupyter.kernels.excludePythonEnvironments": [

.github/workflows/publish.yml

@@ -7,15 +7,19 @@ on:
 
 jobs:
   publish:
-    runs-on: ghcr.io/astral-sh/uv:3.10-bookworm
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
 
     steps:
       - name: Checkout
         uses: actions/checkout@v4
 
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
       - name: Publish package
         run: |
           uv build
           uv publish
-        env:
-          UV_PUBLISH_TOKEN: ${{ secrets.UV_PUBLISH_TOKEN }}

.gitignore

@@ -74,5 +74,8 @@ dist/
 # Terraform
 .terraform/
 
+# uv
+uv.lock
+
 # VS Code
 .vscode/

.pre-commit-config.yaml

@@ -52,13 +52,6 @@ repos:
         require_serial: true
         language: system
         stages: [commit-msg]
-      - id: uv-lock-check
-        name: uv lock check
-        entry: uv lock
-        args: ["--check"]
-        require_serial: true
-        language: system
-        pass_filenames: false
       - id: ruff-check
         name: ruff check
         entry: ruff check

Dockerfile

@@ -15,7 +15,7 @@ RUN git config --system --add safe.directory '*'
 RUN --mount=type=cache,target=/var/cache/apt/ \
     --mount=type=cache,target=/var/lib/apt/ \
     groupadd --gid 1000 user && \
-    useradd --create-home --no-log-init --gid 1000 --uid 1000 user && \
+    useradd --create-home --no-log-init --gid 1000 --uid 1000 --shell /usr/bin/bash user && \
     chown user:user /opt/ && \
     apt-get update && apt-get install --no-install-recommends --yes sudo && \
     echo 'user ALL=(root) NOPASSWD:ALL' > /etc/sudoers.d/user && chmod 0440 /etc/sudoers.d/user

README.md

@@ -40,10 +40,10 @@ RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with Postgr
 ## Installing
 
 > [!TIP]
-> 🚀 It is optional but recommended to install [an accelerated llama-cpp-python precompiled binary](https://github.com/abetlen/llama-cpp-python?tab=readme-ov-file#supported-backends) with:
+> 🚀 If you want to use local models, it is recommended to install [an accelerated llama-cpp-python precompiled binary](https://github.com/abetlen/llama-cpp-python?tab=readme-ov-file#supported-backends) with:
 > ```sh
-> # Configure which llama-cpp-python precompiled binary to install (⚠️ On macOS only v0.3.2 is supported right now):
-> LLAMA_CPP_PYTHON_VERSION=0.3.2
+> # Configure which llama-cpp-python precompiled binary to install (⚠️ not every combination is available):
+> LLAMA_CPP_PYTHON_VERSION=0.3.4
 > PYTHON_VERSION=310|311|312
 > ACCELERATOR=metal|cu121|cu122|cu123|cu124
 > PLATFORM=macosx_11_0_arm64|linux_x86_64|win_amd64
@@ -357,11 +357,9 @@ OPENAI_API_KEY=sk-... raglite --llm gpt-4o-mini --embedder text-embedding-3-larg
 <details>
 <summary>Prerequisites</summary>
 
-<details>
-<summary>1. Set up Git to use SSH</summary>
-
 1. [Generate an SSH key](https://docs.github.com/en/authentication/connecting-to-github-with-ssh/generating-a-new-ssh-key-and-adding-it-to-the-ssh-agent#generating-a-new-ssh-key) and [add the SSH key to your GitHub account](https://docs.github.com/en/authentication/connecting-to-github-with-ssh/adding-a-new-ssh-key-to-your-github-account).
 1. Configure SSH to automatically load your SSH keys:
+
     ```sh
     cat << EOF >> ~/.ssh/config
     
@@ -373,31 +371,9 @@ OPENAI_API_KEY=sk-... raglite --llm gpt-4o-mini --embedder text-embedding-3-larg
     EOF
     ```
 
-</details>
-
-<details>
-<summary>2. Install Docker</summary>
-
 1. [Install Docker Desktop](https://www.docker.com/get-started).
-    - _Linux only_:
-        - Export your user's user id and group id so that [files created in the Dev Container are owned by your user](https://github.com/moby/moby/issues/3206):
-            ```sh
-            cat << EOF >> ~/.bashrc
-            
-            export UID=$(id --user)
-            export GID=$(id --group)
-            EOF
-            ```
-
-</details>
-
-<details>
-<summary>3. Install VS Code or PyCharm</summary>
-
 1. [Install VS Code](https://code.visualstudio.com/) and [VS Code's Dev Containers extension](https://marketplace.visualstudio.com/items?itemName=ms-vscode-remote.remote-containers). Alternatively, install [PyCharm](https://www.jetbrains.com/pycharm/download/).
-2. _Optional:_ install a [Nerd Font](https://www.nerdfonts.com/font-downloads) such as [FiraCode Nerd Font](https://github.com/ryanoasis/nerd-fonts/tree/master/patched-fonts/FiraCode) and [configure VS Code](https://github.com/tonsky/FiraCode/wiki/VS-Code-Instructions) or [configure PyCharm](https://github.com/tonsky/FiraCode/wiki/Intellij-products-instructions) to use it.
-
-</details>
+1. _Optional:_ install a [Nerd Font](https://www.nerdfonts.com/font-downloads) such as [FiraCode Nerd Font](https://github.com/ryanoasis/nerd-fonts/tree/master/patched-fonts/FiraCode) and [configure VS Code](https://github.com/tonsky/FiraCode/wiki/VS-Code-Instructions) or [PyCharm](https://github.com/tonsky/FiraCode/wiki/Intellij-products-instructions) to use it.
 
 </details>
 
@@ -406,9 +382,10 @@ OPENAI_API_KEY=sk-... raglite --llm gpt-4o-mini --embedder text-embedding-3-larg
 
 The following development environments are supported:
 
-1. ⭐️ _GitHub Codespaces_: click on _Code_ and select _Create codespace_ to start a Dev Container with [GitHub Codespaces](https://github.com/features/codespaces).
-1. ⭐️ _Dev Container (with container volume)_: click on [Open in Dev Containers](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/superlinear-ai/raglite) to clone this repository in a container volume and create a Dev Container with VS Code.
+1. ⭐️ _GitHub Codespaces_: click on [Open in GitHub Codespaces](https://github.com/codespaces/new/superlinear-ai/raglite) to start developing in your browser.
+1. ⭐️ _VS Code Dev Container (with container volume)_: click on [Open in Dev Containers](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/superlinear-ai/raglite) to clone this repository in a container volume and create a Dev Container with VS Code.
 1. ⭐️ _uv_: clone this repository and run the following from root of the repository:
+
     ```sh
     # Create and install a virtual environment
     uv sync --python 3.10 --all-extras
@@ -419,13 +396,13 @@ The following development environments are supported:
     # Install the pre-commit hooks
     pre-commit install --install-hooks
     ```
-1. _Dev Container_: clone this repository, open it with VS Code, and run <kbd>Ctrl/⌘</kbd> + <kbd>⇧</kbd> + <kbd>P</kbd> → _Dev Containers: Reopen in Container_.
-1. _PyCharm_: clone this repository, open it with PyCharm, and [configure Docker Compose as a remote interpreter](https://www.jetbrains.com/help/pycharm/using-docker-compose-as-a-remote-interpreter.html#docker-compose-remote) with the `dev` service.
-1. _Terminal_: clone this repository, open it with your terminal, and run `docker compose up --detach dev` to start a Dev Container in the background, and then run `docker compose exec dev zsh` to open a shell prompt in the Dev Container.
+
+1. _VS Code Dev Container_: clone this repository, open it with VS Code, and run <kbd>Ctrl/⌘</kbd> + <kbd>⇧</kbd> + <kbd>P</kbd> → _Dev Containers: Reopen in Container_.
+1. _PyCharm Dev Container_: clone this repository, open it with PyCharm, [create a Dev Container with Mount Sources](https://www.jetbrains.com/help/pycharm/start-dev-container-inside-ide.html), and [configure an existing Python interpreter](https://www.jetbrains.com/help/pycharm/configuring-python-interpreter.html#widget) at `/opt/venv/bin/python`.
 
 </details>
 
-<details>
+<details open>
 <summary>Developing</summary>
 
 - This project follows the [Conventional Commits](https://www.conventionalcommits.org/) standard to automate [Semantic Versioning](https://semver.org/) and [Keep A Changelog](https://keepachangelog.com/) with [Commitizen](https://github.com/commitizen-tools/commitizen).

docker-compose.yml

@@ -5,7 +5,6 @@ services:
       target: dev
     environment:
       - OPENAI_API_KEY
-      - UV_PUBLISH_TOKEN
     depends_on:
       - postgres
     volumes:

pyproject.toml

@@ -1,4 +1,8 @@
-[project] # https://packaging.python.org/en/latest/specifications/pyproject-toml/
+[build-system]  # https://docs.astral.sh/uv/concepts/projects/config/#build-systems
+requires = ["hatchling>=1.27.0"]
+build-backend = "hatchling.build"
+
+[project]  # https://packaging.python.org/en/latest/specifications/pyproject-toml/
 name = "raglite"
 version = "0.6.2"
 description = "A Python toolkit for Retrieval-Augmented Generation (RAG) with SQLite or PostgreSQL."
@@ -11,18 +15,18 @@ dependencies = [
   # Configuration:
   "platformdirs (>=4.0.0)",
   # Markdown conversion:
-  "pdftext (>=0.3.13)",
+  "pdftext (>=0.4.1)",
   "scikit-learn (>=1.4.2)",
   # Markdown formatting:
   "markdown-it-py (>=3.0.0)",
   "mdformat-gfm (>=0.3.6)",
   # Sentence and chunk splitting:
   "numpy (>=1.26.4,<2.0.0)",
-  "scipy (>=1.5.0)",
+  "scipy (>=1.11.2,!=1.15.0.*,!=1.15.1,!=1.15.2)",
   "wtpsplit-lite (>=0.1.0)",
   # Large Language Models:
   "huggingface-hub (>=0.22.0)",
-  "litellm (>=1.57.8)",
+  "litellm (>=1.60.2)",
   "pydantic (>=2.7.0)",
   # Approximate Nearest Neighbors:
   "pynndescent (>=0.5.12)",
@@ -32,11 +36,11 @@ dependencies = [
   "rerankers[flashrank] (>=0.6.0)",
   # Storage:
   "pg8000 (>=1.31.2)",
-  "sqlmodel-slim (>=0.0.18)",
+  "sqlmodel-slim (>=0.0.21)",
   # Progress:
   "tqdm (>=4.66.0)",
   # Evaluation:
-  "pandas (>=2.1.0)",
+  "pandas (>=2.1.1)",
   # CLI:
   "typer (>=0.15.1)",
   # Model Context Protocol:
@@ -58,7 +62,7 @@ issues = "https://github.com/superlinear-ai/raglite/issues"
 
 [dependency-groups]  # https://docs.astral.sh/uv/concepts/projects/dependencies/#development-dependencies
 dev = [
-  "commitizen (>=4.1.0)",
+  "commitizen (>=4.3.0)",
   "coverage[toml] (>=7.6.10)",
   "ipykernel (>=6.29.4)",
   "ipython (>=8.18.0)",
@@ -70,42 +74,42 @@ dev = [
   "pytest (>=8.3.4)",
   "pytest-mock (>=3.14.0)",
   "pytest-xdist (>=3.6.1)",
-  "ruff (>=0.9.2)",
+  "ruff (>=0.10.0)",
   "typeguard (>=4.4.1)",
 ]
 
-[tool.commitizen]  # https://commitizen-tools.github.io/commitizen/config/
-bump_message = "bump(release): v$current_version → v$new_version"
-tag_format = "v$version"
-update_changelog_on_bump = true
-version_provider = "pep621"
-
 [project.optional-dependencies]
 # Frontend:
 chainlit = ["chainlit (>=2.0.0)"]
 # Large Language Models:
-llama-cpp-python = ["llama-cpp-python (>=0.3.2)"]
+llama-cpp-python = ["llama-cpp-python (>=0.3.3)"]
 # Markdown conversion:
 pypandoc-binary = ["pypandoc-binary (>=1.13)"]
 # Evaluation:
 ragas = ["ragas (>=0.1.12)"]
 
-[tool.coverage.report] # https://coverage.readthedocs.io/en/latest/config.html#report
+[tool.commitizen]  # https://commitizen-tools.github.io/commitizen/config/
+bump_message = "bump: v$current_version → v$new_version"
+tag_format = "v$version"
+update_changelog_on_bump = true
+version_provider = "uv"
+
+[tool.coverage.report]  # https://coverage.readthedocs.io/en/latest/config.html#report
 fail_under = 50
 precision = 1
 show_missing = true
 skip_covered = true
 
-[tool.coverage.run] # https://coverage.readthedocs.io/en/latest/config.html#run
+[tool.coverage.run]  # https://coverage.readthedocs.io/en/latest/config.html#run
 branch = true
 command_line = "--module pytest"
 data_file = "reports/.coverage"
 source = ["src"]
 
-[tool.coverage.xml] # https://coverage.readthedocs.io/en/latest/config.html#xml
+[tool.coverage.xml]  # https://coverage.readthedocs.io/en/latest/config.html#xml
 output = "reports/coverage.xml"
 
-[tool.mypy] # https://mypy.readthedocs.io/en/latest/config_file.html
+[tool.mypy]  # https://mypy.readthedocs.io/en/latest/config_file.html
 junit_xml = "reports/mypy.xml"
 strict = true
 disallow_subclassing_any = false
@@ -117,13 +121,13 @@ show_error_codes = true
 show_error_context = true
 warn_unreachable = true
 
-[tool.pytest.ini_options] # https://docs.pytest.org/en/latest/reference/reference.html#ini-options-ref
+[tool.pytest.ini_options]  # https://docs.pytest.org/en/latest/reference/reference.html#ini-options-ref
 addopts = "--color=yes --doctest-modules --ignore=src/raglite/_chainlit.py --exitfirst --failed-first --strict-config --strict-markers --verbosity=2 --junitxml=reports/pytest.xml"
 filterwarnings = ["error", "ignore::DeprecationWarning", "ignore::pytest.PytestUnraisableExceptionWarning"]
 testpaths = ["src", "tests"]
 xfail_strict = true
 
-[tool.ruff] # https://docs.astral.sh/ruff/settings/
+[tool.ruff]  # https://docs.astral.sh/ruff/settings/
 fix = true
 line-length = 100
 src = ["src", "tests"]
@@ -146,10 +150,10 @@ max-doc-length = 100
 [tool.ruff.lint.pydocstyle]
 convention = "numpy"
 
-[tool.uv]  # https://docs.astral.sh/uv/reference/settings/
-package = true
+[tool.poe.executor]  # https://github.com/nat-n/poethepoet
+type = "simple"
 
-[tool.poe.tasks] # https://github.com/nat-n/poethepoet
+[tool.poe.tasks]
 
   [tool.poe.tasks.docs]
   help = "Generate this package's docs"