bRAG-langchain and rag-ecosystem
These are **complements**: bRAG-langchain provides a production-ready RAG framework built on LangChain, while rag-ecosystem offers modular, educational implementations of individual RAG components that can be studied and integrated into frameworks like bRAG.
About bRAG-langchain
bragai/bRAG-langchain
Everything you need to know to build your own RAG application
Structured as progressive Jupyter notebooks using LangChain, covering foundational vector storage with ChromaDB/Pinecone, multi-query retrieval, semantic routing, and advanced techniques like RAPTOR and ColBERT token-level indexing. Demonstrates end-to-end optimization strategies including reciprocal rank fusion, Cohere re-ranking, and self-RAG approaches, with integration points for OpenAI embeddings, LangSmith tracing, and metadata-filtered vector stores.
About rag-ecosystem
FareedKhan-dev/rag-ecosystem
Understand and code every important component of RAG architecture
Implements modular RAG components including query transformations (multi-query, RAG-Fusion, decomposition), intelligent routing (logical and semantic), and advanced indexing strategies (hierarchical, ColBERT). Integrates with LangChain, OpenAI, Cohere, and evaluation frameworks (RAGAS, DeepEval) to enable end-to-end pipeline optimization and grading through self-correcting agentic flows.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work