Navaneethan L·4d agoRetrieval System Design: Beyond the BasicsThe “chunk the PDF, embed it, stuff the top 3 chunks into the prompt” pipeline has a well-defined ceiling.
Everything is MindGame·Sep 27From KNN to HNSW: How Vector Search Scales for Semantic SearchSemantic search and RAG systems often represent text as embedding vectors and then search for documents whose vectors are closest to a…
aravinth C·Aug 11🚀 Running RAGatouille with ColBERT v2.0 on Windows: Problems I Faced and How I Fixed ThemIf you are building a RAG (Retrieval-Augmented Generation) application, you have probably heard of ColBERT.
Aayushi Patel·Aug 3Multi-Vector Retrieval: ColBERT, PLAID, and Late Interaction ModelsTraditional search systems treated documents as single vectors. A document → one embedding → similarity search. That worked well enough for…
