Could someone point me towards a good resource for learning how to build a RAG app without llangchain or llamaindex? It's hard to find good information.
There is probably a simple answer to this question, but why isn't it possible to use a decentralized architecture like in crypto mining to train models?
I'll be refactoring it during this week and then I'll create an article in my blog and a video in my Youtube channel talking about it, in case you are interested :)
How did you get CrewAI working with Llama3? I have got it working by adding "num_predict=128" to the model ChatOllama(), but it's so slow! Any tricks or tips?