rag-time and rag-in-action
These are complementary learning resources that address different aspects of RAG systems—Microsoft's offering provides a structured five-week foundational curriculum, while Huangjia's project delivers hands-on optimization and business-focused implementation across ten RAG components and four real-world scenarios.
About rag-time
microsoft/rag-time
RAG Time: A 5-week Learning Journey to Mastering RAG
Structured curriculum covering retrieval fundamentals, Azure AI Search integration, vector index optimization, multimodal data indexing, and agentic RAG patterns through five weekly modules with video walkthroughs and Jupyter notebooks. Emphasizes practical implementation across knowledge retrieval systems, vector compression techniques, and production-scale deployment patterns using Microsoft's AI stack.
About rag-in-action
huangjia2019/rag-in-action
End-to-end RAG system design, evaluation, and optimization. 极客时间RAG训练营，RAG 10大组件全面拆解，4个实操项目吃透 RAG 全流程。RAG的落地，往往是面向业务做RAG，而不是反过来面向RAG做业务。这就是为什么我们需要针对不同场景、不同问题做针对性的调整、优化和定制化。魔鬼全在细节中，我们深入进去探究。
Implements 10 modular RAG components spanning data loading, chunking strategies, embedding with BGE/HuggingFace, vector storage (Milvus/Chroma), query expansion, re-ranking, and LLM integration with DeepSeek. Provides dual framework support for LangChain and LlamaIndex with GPU/CPU variants across Ubuntu, macOS, and Windows, including evaluation tools like RAGAS and TruLens for system performance benchmarking.
Scores updated daily from GitHub, PyPI, and npm data. How scores work