microsoft/PIKE-RAG
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
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.
Stars
2,372
Forks
224
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.
HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"