RAGElo
Elo-based ranking and evaluation of RAG pipelines
All Skills in This Repository (2)
Pure Emerald Level Indicators
zetaalphavectorcreate-pr-description
Generate PR titles, descriptions, and reviewer suggestions from commits and diffs.
zetaalphavectorreview-pr
Review GitHub pull requests for compliance with RAGElos Factory+Registry architecture, evaluators, and security practices.
Frequently Asked Questions
FAQPage SchemaHow to install RAGElo?▼
Run `npx skills add zetaalphavector/RAGElo --all -g -y` in your terminal to install all skills in this repository globally.
How to compare different RAG pipelines?▼
RAGElo runs pairwise comparisons of answers from multiple pipelines and computes Elo rankings, showing which prompts and settings perform best.
Which LLM providers does RAGElo support?▼
It works with OpenAI, local models via Ollama, and providers like Anthropic, Mistral, and Cohere through the Instructor integration.
Can RAGElo evaluate answers against custom criteria?▼
Yes. Rubric evaluators auto-generate scoring criteria from documents or reference answers, and you can edit weights or add built-in checks like citation quality.
Do I need coding experience to use RAGElo?▼
Basic Python or CLI usage is required for evaluation, while the included PR skills let your agent handle review and documentation tasks from plain-English requests.
Related Repositories in Software Engineering
View All in Software Engineering→
openclawopenclaw
Run a personal AI assistant across your devices and chat apps
obrasuperpowers
Gives coding agents a disciplined workflow from idea to merged code
facebookreact
AI agent skills for building, testing, and porting React core