Cyberflunk

joined 2 years ago
[–] Cyberflunk@lemmy.world 5 points 1 week ago

Fucking cunts.

[–] Cyberflunk@lemmy.world 2 points 2 weeks ago (1 children)

What are you talking about? RAG is a method you use. It only has limitations you design. Your datastore can be whatever you want it to be. The llm performs a tool use YOU define. RAG isn't one thing. You can build a rag system out of flat files or a huge vector datastore. You determine how much data is returned to the context window. Python and chromadb easily scales to gigabytes, on consumer hardware, completely suitable for local rag.

[–] Cyberflunk@lemmy.world 1 points 3 weeks ago (1 children)

I've been using ntfy for years without issue. curious how it's failing you.

[–] Cyberflunk@lemmy.world 1 points 4 weeks ago

Super bummer

[–] Cyberflunk@lemmy.world 2 points 1 month ago

I had to use https://leantime.io/all-about-open-source-project-management/ and ended up not hating it. I think it checks all your boxes