I went ahead and installed it in a proxmox container, was fairly easy on x64 (arm support would be nice). One suggestion: it would be nice to have a short-term memory - a la ChatGPT. With the token limit at 4-8k for GPT-4, it would be nice to take advantage of that with both the "long-term memory" (vector store) but also a "short-term" one (as in, sending the previous questions/answers for context).