Differences

This shows you the differences between two versions of the page.

--- requirements [2025/12/27 19:10] – created robyn
+++ requirements [2025/12/30 04:29] (current) – robyn
@@ Line 1: / Line 1: @@
 ====== Requirements ======
-  - An Avatar, Alt, setup to be an AvaDroid.
+  - An Avatar, Alt, setup to be an AvaDroid.\\ \\
-  - A machine running [[https://docs.docker.com/engine/install/|Docker]] which will host Corrade and AvaDroid. The OS on the machine can be any that can run Docker. It is recommended to install [[https://github.com/portainer/portainer|Portainer]] on Docker.
+  - A machine running [[https://docs.docker.com/engine/install/|Docker]] which will host Corrade and AvaDroid. The OS on the machine can be any that can run Docker. It is recommended to install [[https://github.com/portainer/portainer|Portainer]] on Docker. The Docker Host will need a fixed IP number.\\ \\
-  - A machine, can be the same one, running Ollama and a Selected LLM. This machine requires an NVIDIA GPU with at least 8GB VRAM, more the better at least 12GB recommended. For Second Life, I recommend an uncensored LLM such as [[https://ollama.com/library/llama2-uncensored|llama2-uncensored]]  Ollama is preferred as it can dynamically load and unload LLMs allowing the AI to be used for other tasks.
+  - A machine, can be the same one, running Ollama and a Selected LLM. This machine requires an NVIDIA GPU with at least 8GB VRAM, more the better, at least 12GB recommended. For Second Life, I recommend a LLM such as [[https://ollama.com/library/llama3.1|llama3.1]] to start with.  Ollama is preferred as it can dynamically load and unload LLMs allowing the AI engine to be used for other tasks. The Ollama Server, also, needs a fixed IP number. I do not recommend Dockerising Ollama as it runs well on the Host machine "closer" to the GPU. I recommend Ubuntu 24.04 LTS server.