local-llm-lab

Updating the README and USER_GUIDE to clarify the settings and process when using a containerized version of Ollama. Note that when running a containerized version on an old iMac with an Intel chip set up, performance is SLOW

Adding LICENSE to the repo and note in the README

Added a note to make sure user preferences for chat models and embedding models are checked before use since browser configurations (e.g. private browser) or clearing of browser data can result in lost settings.

Adding a note to the README about this being an educational project with no official connection to either Perplexica or Ollama. User beware.