Recent searches
Search options
@shanselman@hachyderm.ioWow LMStudio is AMAZING. Just works. I set up local models running on my NVidia and was running in 10 minutes! THEN a local proxy that pretends to be an OpenAI endpoint and I'm writing C# chat apps in airplane mode! https://lmstudio.ai Damn near perfect app #ai #chatgpt
@shanselman Oh that’s new; didn’t realise they had an OpenAI-like endpoint too. Don’t think it was there in Dec when I first played with it.
Currently am playing with Ollama which is a kind of docker for LLMs. Ollama plays decently well with the likes of LangChain and llm, but not with Semantic Kernel, which is frustrating.
@shanselman Mozilla provides llamafile which provides as well an openai api endpoint. This is even easier to setup, it is just one file. My main reasons using it is privacy as well as quicker turnaround times.
@shanselman any models you found useful?
@shanselman you can make it work with Microsoft.SemanticKernel too (after forcing a private field)
@shanselman cool!
Have you compared to https://ollama.ai/
? (though I guess there will be a lot of tools that pop up in this space)