yhoshi3/RaLLe

RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models

33
/ 100
Emerging

This tool helps AI researchers and developers working with Large Language Models (LLMs) to quickly build, test, and refine their Retrieval-Augmented LLM (R-LLM) applications. It takes various LLMs and data retrieval methods as input, allowing you to combine them, and outputs performance metrics and prompt insights to optimize your R-LLM's effectiveness. The target user is an AI/ML practitioner focused on improving how LLMs access and use external information.

No commits in the last 6 months.

Use this if you are developing R-LLMs and need a straightforward way to experiment with different retrieval mechanisms, LLM backends, and prompt strategies, then objectively evaluate their performance.

Not ideal if you are an end-user simply looking to apply an existing R-LLM solution, rather than actively developing or evaluating one.

AI Development Natural Language Processing LLM Engineering AI Model Evaluation Information Retrieval
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

55

Forks

4

Language

Python

License

MIT

Last pushed

Oct 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/yhoshi3/RaLLe"

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