Sublime

You can make RAG apps 10x smarter with this SOTA method! ColiVara is a retrieval method that does not involve chunking. Instead, it treats docs as images and uses vision models for embedding, just like a human would do. This provides far better accuracy than traditional RAG systems that rely... See more

Graph-powered RAG in 1100 lines of pure hackable code. Build knowledge graphs from your text data using local or distributed components. Query using graph-aware retrieval. Supports async operations, custom LLMs, and different vector/graph storage backends. What it... See more

deepseek is a side project. https://t.co/5SHPJolMVM

This is an excellent tutorial by @mesudarshan showing you how to build advanced PDF RAG with LlamaParse and purely local models for embedding, LLMs, and reranking (@GroqInc and FastEmbed by @qdrant_engine, flag-embedding-reranker) Having a good extraction step is super important and is inherently coupled with good... See more