mangopy/direct-rag-learning

Official code for TOIS2026 "Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models"

39
/ 100
Emerging

This project helps improve the performance of large language models (LLMs) used for answering questions or generating text based on a specific body of knowledge. It takes a collection of documents and a set of questions, then outputs a more accurate and relevant LLM. This is for AI/ML engineers and researchers who build and deploy knowledge-grounded LLM systems.

276 stars.

Use this if you are developing or deploying retrieval-augmented generation (RAG) models and want to enhance the synergy between how knowledge is selected and how answers are generated.

Not ideal if you are new to developing with large language models or do not have experience with model training and optimization workflows.

natural-language-processing question-answering-systems information-retrieval large-language-models generative-ai
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

276

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Jan 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/mangopy/direct-rag-learning"

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