xiami2019/UAR

[Findings of EMNLP'2024] Unified Active Retrieval for Retrieval Augmented Generation

14
/ 100
Experimental

This project helps developers build more efficient and accurate Retrieval-Augmented Generation (RAG) systems. It takes in user instructions and existing knowledge bases, then intelligently decides whether to retrieve external information for each query. The output is a more refined RAG workflow that avoids unnecessary retrievals, improving response quality and reducing computational cost. It is designed for engineers and researchers who are building and optimizing conversational AI and question-answering systems.

No commits in the last 6 months.

Use this if you are developing RAG applications and need to improve the precision and efficiency of information retrieval, ensuring external knowledge is only sought when truly beneficial for generating responses.

Not ideal if you are looking for a pre-built RAG application or a solution that doesn't require deep technical understanding of model training and deployment.

conversational AI development large language models information retrieval optimization natural language processing AI system architecture
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

23

Forks

Language

Python

License

Last pushed

Sep 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/xiami2019/UAR"

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