yudataguy/RawRAG

Let's RAG it RAW without fancy frameworks

30
/ 100
Emerging

This project helps Python developers build their own Retrieval-Augmented Generation (RAG) systems from scratch. It provides practical examples and code to understand the internal workings of RAG. Developers input raw text data or documents and configure retrieval and generation steps to produce tailored, context-aware responses from a language model.

No commits in the last 6 months.

Use this if you are a Python developer who wants to build a RAG system and gain deep control and understanding over every component, without relying on high-level frameworks.

Not ideal if you need to quickly prototype a RAG system with minimal coding or prefer using established, feature-rich frameworks like LangChain or LlamaIndex.

Python development natural-language-processing large-language-models information-retrieval machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

27

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/yudataguy/RawRAG"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.