code

Self-RAG (Self-Reflective Retrieval-Augmented Generation) is a framework that combines the benefits of retrieval-augmented generation (RAG) with self-reflection, allowing large language models (LLMs) to adaptively retrieve passages on-demand and generate more accurate responses. Langgraph recently published a blog post on Self-RAG with their own implementation. I really like the idea of validating the retrieved information. In that past I have noticed that, while vector databases will return documents that usually match the input query string, some may contain irrelevant content....

It’s been few weeks since my last update. I have been quite busy working on a lot of interesting stuff. Some related to this project, some a bit less. Here is a preview of the Dynamic lightning I have been working on. It’s not live for now since it needs a lot of small adjustments before being 100% usable.

Ok now it’s getting a bit more serious. We can now create, save and restore maps in the editor: This tool is available here: https://encounters.4sh.dev Edit: Added support for video maps:

I’m still playing with canvas and I plugged the dungeon generator I worked on a year ago. This is the result: This tool is available here: https://encounters.4sh.dev

The context With the COVID-19 and the shelter in place, there is not much opportunities to play D&D face to face with friends. Some groups decided to go to platforms like Roll20 or Fantasy Ground. While I love those apps they are lacking something in my opinion: an integration with DnD Beyond. I personally have a LOT of digital content on DnD Beyond and the idea of buying it again on another platform is not something I am considering....