MemoRAG is a cutting-edge RAG framework utilizing an advanced memory model to deliver more accurate and contextually rich responses by recalling query-specific clues from a global dataset. It supports long contexts (up to one million tokens), optimizes performance with minimal training, and implements efficient caching and context reusability. Active development is ongoing with various models and tools available in its repository.

9m read timeFrom github.com
Post cover image
Table of contents
OverviewMemoRAG Demo📃 Changelog✨ Features🔎 Roadmap🚀 Quick Start📓 Usage🙌 FAQs🔖 LicenseCitation

Sort: