In the first post, I covered the initial architecture for building a production Django RAG chatbot without turning it into an expensive science project. The first version used a straightforward retrieval path: embed the user’s question, search PostgreSQL with pgvector, pass the retrieved context to the LLM, and log enough…
If you spend enough time in local AI communities, it's easy to come away with the impression that you've discovered a loophole. Run models on your own hardware, and you'll avoid subscription fees. Keep your data private. Stop worrying about token limits and API pricing. Take back control from large…
Over the past year or two, I've had more conversations than I can count about AI and what it means for the future of work. Somewhere along the way, the conversation almost always shifts to content creation. "Why would anyone still write blogs?" It's a reasonable question. AI can generate…
I recently went down the rabbit hole of getting a Darkan world server running under CubeCoders AMP. Darkan is an open-source/community RuneScape private server project with its own cache, client, world server, and lobby architecture. The server is based on circa-2012 content. The setup is not a one-click AMP template,…
In February 2023, Maurice Kevenaar and I started discussing an idea that, at the time, felt both ambitious and a little uncertain. Many Veeam User Groups were still trying to regain momentum following the COVID-19 pandemic. The appetite for connection and learning was still there, but the dynamics had changed.…