RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

AI support agent using Azure Foundry, RAG, Terraform

Reasoning-based, vectorless RAG over a large document using a hierarchical tree (PageIndex) and a Vision-Language Model (Llama 4 Scout), no embeddings, no vector store, no text chunking.

SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning.

LLM-readable debugging knowledge base: structured pits that help coding agents find buried fixes in human-oriented threads.

A TypeScript demo of Azure AI Search agentic retrieval with NASA data

An enterprise view into Agentic Retrieval for Multi-language usecases

Intercepts an AI agent's action before it runs, grounds it in cited precedent via Foundry IQ, pauses for a human.

Modular local RAG pipeline with agentic retrieval, cross-encoder reranking, and context compression. Built with LlamaIndex, ChromaDB, and Ollama. Supports any document collection (txt, json, csv, pdf, html, code). Fully offline — no API keys, no cloud. Configurable persona for prompt engineering, code Q&A, or documentation search.