FareedKhan-dev/rag-with-rl
Maximizing the Performance of a Simple RAG using RL
This project helps anyone building applications that use Large Language Models (LLMs) to answer questions based on a set of provided documents. It takes your documents and questions, and instead of just retrieving information, it uses a "Reinforcement Learning (RL)" approach to select the most relevant document chunks more effectively. This leads to more accurate answers from the LLM, making it valuable for anyone developing AI-powered information retrieval or Q&A systems.
No commits in the last 6 months.
Use this if you are developing an AI system that answers user questions based on a specific set of documents and you are finding that your LLM sometimes provides inaccurate answers due to insufficient or irrelevant context.
Not ideal if you are looking for a complete, production-ready RAG application or if your primary goal is general-purpose LLM fine-tuning without a focus on document-based Q&A.
Stars
90
Forks
24
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/FareedKhan-dev/rag-with-rl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
hienhayho/rag-colls
Collection of recent advanced RAG techniques.
jeremiahbohr/literature-mapper
Transform academic PDFs into a Knowledge Graph with typed claims, temporal analysis,...