News for hackers. Stuff that matters.

A comment on RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI. Parent comment

Re:RasaGPT: First headless LLM chatbot built on top of Rasa,... by Dowwie on Monday May 08, 2023 @02:14PM (#35865072)
Are these computationally expensive operations? If not, Elixir could fit.
[ Parent | on HN ]
Re:RasaGPT: First headless LLM chatbot built on top of Rasa,... by krishadi on Thursday May 11, 2023 @03:57AM (#35899151)
They are not all computationally expensive. The rate limiting step here is the LLM call itself over the API. So, async is definitely needed. The other aspects would be loading the template from filesystem. I would assume this could be something that's needs to be optimized in the application.
[ Parent | on HN ]