advanced-rag

This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.

This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models for generation and evaluation.

All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers

Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.

Building a multi-agent RAG system with advanced RAG methods

It shows an advanced RAG with Reflection where LangGraph is used for workflow management.

Multiple Coder assistants: This project leverages Language Model (LLM) agents to generate code snippets for users, providing assistance in various programming tasks. Additionally, it constructs a knowledge bank that can be referenced to aid in code creation for individual references.

The only prototyping Multi-Agent systems repo you will need, running on dockers

A practical cookbook of 10 Advanced RAG techniques — Naive, Hybrid, HyDE, Fusion, Parent-Child, RRR, Contextual Compression, and more. Working code + real benchmarks + plain-English explanations.

This repo is for advanced RAG systems, each branch will represent a project based on RAG.

AI-powered Indian legal intelligence platform — multi-agent LangGraph system with hybrid RAG, 6-layer memory architecture, and LLM-based intent classification. Helps citizens understand their legal rights.

A multi-agent chat application combining flight search, news retrieval, and financial document analysis using LangGraph and advanced RAG. Features a hybrid search strategy with BM25, vector similarity, and MMR, enhanced by Cohere re-ranking for accurate document retrieval.

Viewed README.md:1-192 This Research Agent is an AI-powered tool that uses a ReAct loop to dynamically search, summarize, and compare research papers from a collection of PDFs. Unlike simple RAG, it autonomously orchestrates multi-step workflows to synthesize findings, identify research contradictions, and generate comprehensive gap analysis rep

단순 검색을 넘어선 실전형 Advanced RAG 백엔드. 하이브리드 검색(RRF), 동적 리랭킹, 그리고 환각(Hallucination) 제어 파이프라인을 구축한 RAG 프로젝트입니다

Agentic RAG system with five workflow modes from Naive to Deep, routing each question to the cheapest path that answers it well, fusing dense and BM25 retrieval through Reciprocal Rank Fusion with CrossEncoder reranking, verifying groundedness and citations, and gating risky answers behind a human-in-the-loop approval queue.

"A theoretical framework and implementation for governing LLMs via Digital Wave Dynamics, latent space topology, and non-linear state control." "A mathematical and physical approach to LLM internals: Exploring digital wave mechanics, topological manifolds, and mechanistic interpretability."

Advanced Retrieval-Augmented Generation (RAG) system for chatting with an Obsidian knowledge base using LangChain, ChromaDB, Hugging Face embeddings, CUDA acceleration , Hybrid Search and Reranking

AgenticFit is a production backend that pairs classical ML (LightGBM/XGBoost with MLOps), advanced RAG (HyDE + hybrid retrieval + cross-encoder reranking), and multi-agent AI systems (LangGraph, CrewAI) to deliver personalized health intelligence. Deployed on HuggingFace Spaces, serving a React 19 frontend on Vercel.