:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Sorry for the naive question, but I am really new to this. So, do you expect numpy functions to be converted to math functions in the code wherever possible?
Numpy is an heavy library to import and we overuse it all around the codebase.
We should remove it and fallback to use builtin
math
whenever possible to speed up import speed.