xmpuspus/kb-arena

Benchmark 7 retrieval strategies on your own docs — naive vector, contextual, QnA pairs, knowledge graph, RAPTOR, PageIndex, and hybrid. Find which KB architecture fits your data.

54
/ 100
Established

Implements 8 retrieval strategies (including BM25, knowledge graphs, and RAPTOR) that run in parallel with pluggable LLM backends (Anthropic, OpenAI, Ollama) and auto-generates multi-tier benchmark questions from your documents. Ships a bundled React dashboard with strategy Arena mode for blind A/B comparison, cost tracking per strategy, and CI/CD integration via `--fail-below` thresholds—designed specifically for architecture selection rather than pipeline evaluation.

Available on PyPI.

Maintenance 13 / 25
Adoption 10 / 25
Maturity 18 / 25
Community 13 / 25

How are scores calculated?

Stars

6

Forks

2

Language

Python

License

MIT

Last pushed

Mar 20, 2026

Monthly downloads

518

Commits (30d)

0

Dependencies

19

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/xmpuspus/kb-arena"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.