di37/rag-from-scratch
Demo done in a jupyter notebook to show how Retrieval Augmented Generation (RAG) can be done without using any frameworks.
This project helps developers understand the core mechanics of Retrieval Augmented Generation (RAG) by demonstrating how to build a basic RAG system without relying on external frameworks. It takes raw text data as input and illustrates the process of retrieving relevant information and generating augmented responses. This is ideal for AI/ML developers or researchers who want to deeply grasp RAG principles.
No commits in the last 6 months.
Use this if you are a developer or researcher who wants to learn the fundamental components of a RAG system by building one from the ground up, without framework abstractions.
Not ideal if you need a production-ready RAG system or want to quickly implement RAG using established libraries and tools.
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
shivamsanju/ragswift
🚀 Scale your RAG pipeline using Ragswift: A scalable centralized embeddings management platform
martin-fabbri/next-gen-rag
Advancing the next generation of Retrieval Augmented Generation (RAG): A dynamic exploration of...
FareedKhan-dev/speed_up_your_RAG_app
Speed up your RAG by performing cosine similarity parallel on your CPU Cores
VectorBoard/vectorboard
Open Source Embeddings Optimisation and Eval Framework for RAG/LLM Applications. Documentations...