Training code for advanced RAG techniques - Adaptive-RAG, Corrective RAG, RQ-RAG, Self-RAG, Agentic RAG, and ReZero. Reproduces paper methodologies to fine-tune LLMs via SFT and GRPO for adaptive retrieval, corrective evaluation, query refinement, self-reflection, and agentic search behaviors.

A chat-based AI travel planning assistant that helps users create personalized travel itineraries using real-time data from TripAdvisor

Agentic Adaptive RAG is a production-ready framework for building self-correcting, reasoning-based LLM systems that dynamically choose between retrieval, web search, and generation.

"A resilient RAG agent built with LangGraph and LlamaIndex that self-corrects by rewriting queries when retrieval quality is low. Features a cyclical graph architecture for adaptive search.

Production-style Adaptive RAG chatbot for university course selection (PolyU). Hybrid search (BM25 + dense vector via ChromaDB), Reciprocal Rank Fusion, parent-child chunking, query decomposition, multi-turn conversation. Built with FastAPI + LangChain + Qwen. Includes evaluation suite + ablation study + bundled Claude tutor skill.

adaptive rag, corrective rag and agentic rag examples using langgraph

Adaptive RAG is an advanced retrieval-augmented generation system that intelligently combines dynamic query analysis with self-corrective mechanisms to choose the most effective strategy for answering user queries.

Deep Agentsライブラリのアーキテクチャを活用した、ハーネス構成のRAGシステムです。複数のエージェントが協調動作し、質問の粒度に応じて最適なRAGシステム（Naive RAG / ColBERT RAG）を自動選択します。

Context-aware tool for automated BDD test generation and execution using RAG, VectorDB, and LLaMA.

Enhanced adaptive RAG system with multi-turn reasoning and reflective query decomposition.

An attempt to production-ready Retrieval-Augmented Generation (RAG) system with advanced features including hybrid retrieval, adaptive feedback loops, comprehensive evaluation, and explainable AI logging.

This project implements an advanced Adaptive Retrieval-Augmented Generation (RAG) agent using FastAPI and LangGraph. Unlike static RAG pipelines, this agent employs a cognitive architecture that dynamically selects data sources, optimizes retrieval through query translation and fusion, and verifies its own outputs using self-reflection mechanisms.

Advanced RAG using langgraph which uses websearch functionality to produce relevant documents.

This repository serves as knowledge base. The main focus is on the practical application of large models, including industry data fine-tuning, large model evaluation, and large model applications. All content is structured for easy navigation and learning.

🔍 Enhance your searches with Self-Corrective RAG, a system that optimizes queries and evaluates document relevance using LangGraph and Google Gemini.