Content
@
0 reply
0 recast
0 reaction
ccarella
@ccarella.eth
I am now running my own local LLM server at home via Ollama. Playing with models but liking llama2 with all the AI safety features turned off. It's connected to my Obsidian knowledge base but want to augment (RAG) it a lot more. One custom gpt so far around Product Desigb. Can access via mobile when out of the home.
10 replies
3 recasts
93 reactions
ccarella
@ccarella.eth
Will hook up Stable diffusion to it soon and will write a few bespoke apps.
0 reply
0 recast
2 reactions
drewcoffman
@drewcoffman.eth
are you still doing this / using this?
1 reply
0 recast
0 reaction
Ottis Ots
@ottis
Impressive, ccarella! 50 $RARE 💎
1 reply
0 recast
0 reaction
Jamie Dubs
@jamiew
how are you accessing it remotely? Love idea of wiring it up to my Obsidian; especially if I can use on the go
1 reply
0 recast
0 reaction
Taye 🎩🔵 👽⛏️
@casedup
What you plan on doing with it? What made you do a homebrew?
1 reply
0 recast
1 reaction
Ben - [C/x]
@benersing
What's been the biggest learning in setting it up?
1 reply
0 recast
0 reaction
chris 🤘🏻
@ckurdziel.eth
this is pretty awesome. is there a primer on how to set this up? and what kind of hardware do you need to do it?
1 reply
0 recast
1 reaction
Mike
@mlke19
great
0 reply
0 recast
0 reaction
Andy C
@ajchatham
Working on something similar, really liking Ollama. Why not pull down Llama3? My goal is to add RAG with links to my smart home devices, /dimo , an inventory of tools and food shopping lists, and a calendar of maintenance tasks. Would be good to compare notes & setups at some point
0 reply
0 recast
0 reaction
Rika
@rikasukenik.eth
Awesome! I was using the second brain plugin in Obsidian to try querying my notes. Have you by chance tried it?
0 reply
0 recast
0 reaction
![Ben - [C/x] pfp](https://i.imgur.com/qdfZSol.gif)
