rag-zero-to-hero-guide and rag-all-in-one
These are **competitors** — both are educational guides teaching RAG fundamentals and application development, so a learner would choose one comprehensive resource rather than use both in parallel.
About rag-zero-to-hero-guide
KalyanKS-NLP/rag-zero-to-hero-guide
Comprehensive guide to learn RAG from basics to advanced.
Covers implementation patterns across multiple frameworks (LangChain, CrewAI) and evaluation methodologies using dedicated tools like RAGAS and DeepEval for measuring retriever and generator performance. Includes practical notebooks demonstrating RAG pipelines on diverse data sources—from raw documents to web content and video transcripts—alongside a curated toolkit spanning vector databases (FAISS, Qdrant, Weaviate), document parsers (Docling, Llama Parse), and chunking strategies.
About rag-all-in-one
lehoanglong95/rag-all-in-one
🧠 Guide to Building RAG (Retrieval-Augmented Generation) Applications
Provides a curated directory of 15+ RAG pipeline components—from document ingestion and chunking to vector databases, LLM providers, and evaluation frameworks—with integrated links to courses, tools, and complete reference implementations. Covers advanced techniques including multimodal RAG, knowledge graph integration, hybrid search systems, and production deployment patterns across platforms like LangChain, LlamaIndex, and LLMWare. Functions as both a learning progression guide and a technology stack navigator for developers building end-to-end RAG systems.
Scores updated daily from GitHub, PyPI, and npm data. How scores work