Too many programmers think they have a unique use case without considering that maybe the existing projects are bloated for a reason. Then they end up just recreating the same bloat.
When I was looking at your library last week, It didn't look like there was a direct way to use my own embedding model endpoints. For example, I run snowflake arctic embed in vllm and it would be good be able to use it with Chonkie's semantic chunkers.
Ollama has a really good perk in that it makes it trivial which model is loaded and unloaded from the GPU. So if you're using a frontend like librechat or openwebui, then switching models is as easy as picking from the drop down without having to fiddle with the command line.
You mean like how tobacco company CEO's went to Congress telling them that there is no cancer risk? Oil companies pretending they didn't know about global warming? Shrinkflation? Corporations lie all the time and the people running them are never punished.