rag-from-scratch and production-rag

The "rag-from-scratch" tool, focused on demystifying RAG by building it from the ground up, could serve as an educational complement to "production-rag," which aims to enhance retrieval accuracy with a production-ready system integrating semantic and lexical search, as the former provides the foundational understanding necessary to effectively implement and troubleshoot the advanced features of the latter.

rag-from-scratch
59
Established
production-rag
24
Experimental
Maintenance 16/25
Adoption 10/25
Maturity 13/25
Community 20/25
Maintenance 13/25
Adoption 0/25
Maturity 9/25
Community 2/25
Stars: 1,239
Forks: 135
Downloads:
Commits (30d): 3
Language: JavaScript
License: MIT
Stars:
Forks: 1
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About rag-from-scratch

pguso/rag-from-scratch

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

Implements a modular, JavaScript-based RAG pipeline with progressive learning examples covering embeddings, in-memory vector indexing, and retrieval strategies including hybrid search, multi-query decomposition, and query rewriting with LLM fallbacks. Built entirely with local models (via node-llama-cpp) and includes reusable library components for caching, normalization, and result fusion techniques like reciprocal rank fusion.

About production-rag

mahdidjemaci/production-rag

🔍 Enhance retrieval accuracy with a production-ready RAG system that integrates semantic and lexical search for optimal results.

Scores updated daily from GitHub, PyPI, and npm data. How scores work