di37/rag-from-scratch
Demo done in a jupyter notebook to show how Retrieval Augmented Generation (RAG) can be done without using any frameworks.
Implements core RAG components—document chunking, vector embeddings, similarity search, and LLM integration—using only standard Python libraries without external ML frameworks. The notebook demonstrates the complete retrieval pipeline from raw documents through semantic matching to prompt augmentation, making the underlying mechanics transparent rather than abstracted away.
No commits in the last 6 months.
Stars
16
Forks
—
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Aug 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/di37/rag-from-scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LongxingTan/open-retrievals
All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers
axiom-llc/axiom-rag
Production RAG pipeline — grounded retrieval, source-cited answers, Precision@k + MRR eval. CLI...
ereztdev/RAGOps
AI powered troubleshooting for ground support equipment. Deterministic RAG pipeline that ingests...
AdnanSattar/Spatial-RAG
A production-ready full-stack system that combines semantic search with spatial proximity to...
shivamsanju/ragswift
🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform