OpenParable
Skip to content
← Back to skills

Rank LLM Install

Development
rank-llm-install

Rank LLM Install is an Agent Skill for development published in the castorini/rank_llm repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Set up a rank_llm development environment. Use when someone is onboarding, setting up a fresh clone, choosing extras such as cloud, api, local, or pyserini, or troubleshooting whether the packaged rank-llm CLI is ready.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/castorini/rank_llm/blob/HEAD/.claude/skills/rank-llm-install/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/rank-llm-install, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

rank_llm Install

Development environment setup for rank_llm and its packaged rank-llm CLI.

Prerequisites

  • Python 3.11+
  • Git
  • Java 21 only for retrieval or evaluation workflows that use pyserini

Verify Runtime

python3 --version
command -v uv

If uv is on PATH, use it silently. If not, ask once whether to install uv or continue with a fallback pip or conda path.

Clone (if needed)

If no pyproject.toml is present:

git clone [email protected]:castorini/rank_llm.git && cd rank_llm

Install (source - preferred)

uv path

uv python install 3.11
uv venv --python 3.11
source .venv/bin/activate
uv sync --group dev --extra cloud --extra api

pip path

python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[cloud,api]"
pip install pre-commit

conda fallback

conda create -n rankllm python=3.11 -c conda-forge -y
conda activate rankllm
pip install -e ".[cloud,api]"

PyPI alternative

uv pip install rank-llm

Smoke Test

rank-llm --output json doctor
rank-llm --help

Pre-commit (source installs)

uv run pre-commit install --install-hooks --hook-type pre-commit --hook-type pre-push

Reference Files

  • references/extras.md - Optional extras and when to add them

Gotchas

  • rank-llm is the canonical CLI entry point. The legacy scripts under src/rank_llm/scripts/ remain available, but they are compatibility wrappers.
  • cloud is the default hosted-provider stack and api is the lightweight HTTP server stack. This pair is the best default for most contributor workflows.
  • pyserini requires Java 21 and is only needed for retrieval or evaluation workflows.
  • local, vllm, and sglang pull in heavier inference stacks. Do not install them by default.