kyopark2014/agentic-rag

It shows how to realize agentic RAG.

44
/ 100
Emerging

This project provides practical examples for improving how AI models answer questions using your own documents, a process called Retrieval Augmented Generation (RAG). It shows you how to input various document types like PDFs, extract relevant information, and then use that information to generate more accurate and helpful responses from an AI. This is for AI application developers and engineers who want to build more reliable and intelligent conversational AI systems.

No commits in the last 6 months.

Use this if you are building generative AI applications and need to improve the accuracy and relevance of AI responses by integrating specific knowledge from your own document repositories.

Not ideal if you are a non-technical user looking for a ready-to-use AI chatbot without wanting to dive into system architecture or coding.

AI application development Generative AI Natural Language Processing Information Retrieval Conversational AI
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

28

Forks

19

Language

Python

License

Apache-2.0

Last pushed

Jun 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/kyopark2014/agentic-rag"

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