ALucek/custom-rag-evals

Applying domain specific evaluations to RAG chunking and embedding functions

26
/ 100
Experimental

This project helps you optimize how your documents are prepared for a Retrieval Augmented Generation (RAG) system. It takes your specific documents and various text splitting and embedding methods, then tells you which combination provides the best results for accurately retrieving information. This is for AI developers or data scientists building custom RAG applications who need to ensure high-quality information retrieval.

No commits in the last 6 months.

Use this if you are building a RAG system and need to determine the most effective way to break down your unique documents and embed them for optimal information retrieval.

Not ideal if you are looking for a pre-built RAG application or a simple plug-and-play solution without needing to evaluate underlying strategies.

AI-development RAG-system-optimization natural-language-processing information-retrieval LLM-application-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

18

Forks

3

Language

Jupyter Notebook

License

Last pushed

Dec 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/ALucek/custom-rag-evals"

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