microsoft/PIKE-RAG

PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation

48
/ 100
Emerging

Implements multi-level knowledge extraction and organization pipelines—from context-aware document segmentation and term-alias alignment to knowledge-centric reasoning—enabling domain-specific RAG beyond simple embedding-based retrieval. Achieves 87.6% accuracy on HotpotQA and 59.6% on MuSiQue through modular architecture supporting factual retrieval, multi-hop reasoning, and task decomposition via multi-agent planning. Targets industrial applications (manufacturing, pharmaceuticals, mining) with configurable YAML-based pipelines and Python framework for custom component integration.

2,372 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

2,372

Forks

224

Language

Python

License

MIT

Last pushed

Sep 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/microsoft/PIKE-RAG"

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