DEEP-PolyU/LinearRAG
Source code of LinearRAG at ICLR'26
This project helps AI application developers build efficient Retrieval-Augmented Generation (RAG) systems, especially for large datasets. It takes a collection of documents or text and processes them into a graph structure, which is then used by a Large Language Model (LLM) to answer complex questions or generate informed responses. The end-users are developers working on AI applications that require accurate, context-aware information retrieval from vast text corpora.
421 stars.
Use this if you are a developer building RAG applications and need to reduce the computational cost and time associated with constructing knowledge graphs from very large text datasets, particularly when context preservation and multi-hop reasoning are critical.
Not ideal if you are a business user looking for a ready-to-use RAG application, as this is a developer tool that requires technical setup and coding knowledge.
Stars
421
Forks
45
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/DEEP-PolyU/LinearRAG"
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,...