Stop Shoving Documents Into LLMs: Build a Local Summarizer with Docling + RAG

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…

Fetching and Analysing Web Content with LLMs in C#

📌 Note: This article teaches the fundamentals of web content extraction with LLMs using the simplest possible approach. For production use cases (web summarization, document analysis, agent tools), see DocSummarizer GitHub release - it implements the…

How to Analyse Large CSV Files with Local LLMs in C#

Series: Local LLMs for Data - Part 1 of 2 Here's the mistake everyone makes: they try to feed their CSV into an LLM. Don't. LLMs should generate queries, not consume data. You've got a 500MB CSV file and want to ask "What's the average order value by region?"…

Why I Don't Use LangChain (and What I Do Instead)

I'm a .NET developer. When I started building LLM-powered systems, everyone pointed me toward LangChain. "It's the standard," they said. "All the examples use it." And they were right - if you're in the Python ecosystem, LangChain is everywhere. But here's the…

Building a "Lawyer GPT" for Your Blog - Part 9: Document Ingestion with Docling

Welcome to Part 9! In previous parts, we've built a robust RAG system that processes markdown blog posts and makes them searchable through semantic embeddings. Now it's time to expand our capabilities with Docling - a powerful document processing library that…

Using CSX Scripts for Quick C# Testing

Need to test a snippet of C# code without spinning up a full project? C# Script files (.csx) let you write and run C# code like a scripting language. No Program.cs, no .csproj, no build step - just write and run. Perfect for testing APIs, validating logic, or…

Under Pressure: How Queueing Systems Handle Backpressure with Examples in C#

Backpressure is the unsung hero of distributed systems. It's what keeps your queues from bursting at the seams when producers are firing messages faster than consumers can chew through them. Put simply: it's the system saying "hold on a moment" when things get…

The War on 404: Making Old Stuff Work Again

When you've been blogging since 2004 (yes, really), you accumulate a lot of digital detritus. I recently imported my old posts from 2004-2009 ( https://www.mostlylucid.net/blog/category/Imported) and discovered that approximately everything was broken.…

Towards 1.0: Making Umami.NET Production Ready

When I first integrated Umami analytics into my blog platform, I quickly ran into a frustrating reality: Umami's API documentation is... let's be charitable and call it "minimal." Error messages are cryptic at best, non-existent at worst. Parameters change…

Building a "Lawyer GPT" for Your Blog - Part 8: Advanced Features & Production Deployment

WARNING: THESE ARE DRAFT POSTS WHICH 'ESCAPED'. It's likely much of what's below won't work; I generate these as how-to for ME and then do all the steps and get the sample app working...You've been sneaky and seen them! they'll likely be ready mid-December.…