// Set up a nuggetizer development environment — checks Python 3.11+, installs via uv or pip, and verifies with doctor. Use when someone is onboarding, setting up a fresh clone, or troubleshooting their environment.
| name | nuggetizer-install |
| description | Set up a nuggetizer development environment — checks Python 3.11+, installs via uv or pip, and verifies with doctor. Use when someone is onboarding, setting up a fresh clone, or troubleshooting their environment. |
Development environment setup for nuggetizer — nugget creation, assignment, and evaluation.
github.com:castorini)python3 --version # must be 3.11+
command -v uv # if present, use uv path; otherwise recommend uv
If uv is on PATH, use it silently. If not, ask the user once: install uv or proceed with pip.
If no pyproject.toml in cwd:
git clone git@github.com:castorini/nuggetizer.git && cd nuggetizer
uv venv --python 3.11
source .venv/bin/activate
uv sync --group dev
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
pip install pre-commit pytest mypy ruff
pip install nuggetizer
nuggetizer doctor --output json
nuggetizer --help
pre-commit install
references/extras.md — Optional dependency details (read when user asks about specific backends)disallow_untyped_defs = true. All new functions need type annotations.[dependency-groups] in pyproject.toml is a PEP 735 feature — not pip-installable directly. Use uv sync --group dev or install dev deps manually with pip.tests/ (with an s).Use when analyzing nuggetizer metrics outputs — comparing runs, computing agreement between models, reporting token usage and latency from trace fields, and building side-by-side evaluation tables. Use after running metrics to interpret and compare results.
Use when validating nuggetizer batch outputs — checks JSONL integrity, duplicate qids, missing nugget fields, assignment label validity, and metrics consistency. Wraps `nuggetizer validate` plus custom assertions. Use after running create, assign, or metrics to verify output correctness.
Use when working with nuggetizer CLI commands (create, assign, metrics), prompt templates, JSONL formats, or introspection (doctor, describe, schema, validate). Covers all entry points, flags, and the YAML prompt system.