Your RAG system is great at "needle" questions: retrieve a few relevant chunks and synthesise an answer. It struggles with two common query types: Sensemaking: "What are the main themes across this corpus?" Connective: "How does X relate to Y across different…
GitHub release .NET Version This is Part 2 of the DocSummarizer series. See Part 1 for the architecture and patterns, or Part 3 for the deep technical dive into embeddings and retrieval. Turn documents or URLs into evidence-grounded summaries - for humans or…
Here's the mistake everyone makes with document summarization: they extract the text and send as much as fits to an LLM. The LLM does its best with whatever landed in context, structure gets flattened, and the summary gets increasingly generic as documents get…
📖 Part of the RAG Series: This is Part 4a - core implementation: Part 1: RAG Origins and Fundamentals - What embeddings are, why they matter Part 2: RAG Architecture and Internals - Chunking, tokenisation, vector databases Part 3: RAG in Practice - Building…
📖 Related to the RAG Series: This article provides a deep dive into Qdrant, the vector database used in: Part 4: ONNX & Qdrant Implementation - Building semantic search Part 5: Hybrid Search & Auto-Indexing - Production integration Qdrant (pronounced…
📖 Part of the RAG Series: This is Part 5 - production integration patterns: Part 1: RAG Origins and Fundamentals - What embeddings are, why they matter Part 2: RAG Architecture and Internals - Chunking, tokenisation, vector databases Part 3: RAG in Practice -…
In my 8-part "Lawyer GPT" series, I showed you how to build a complete local RAG-based writing assistant using GPU acceleration, local LLMs, and vector databases. It's powerful, private, and runs entirely on your hardware. But let's be honest - not everyone…