This project implements various Retrieval-Augmented Generation (RAG) techniques to analyze AWS case studies and technical blog posts using local LLMs (via Ollama) and local embeddings. It demonstrates ...
An enterprise-grade, local-first multi-agent research assistant. This project abandons the traditional (and often brittle) ReAct agent loop in favor of a Plan-and-Execute architecture. By decoupling ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results