Setup Obsidian AI With LM Studio | YOUR OWN AI

[@SystemSculpt]

Did you see part 1? Yesterday's Video (part 1): kzbin.info/www/bejne/bYDGqKqPqbCmm8U Just finishing the script up to automate our testing, and we're good to go! So excited for tomorrow's video. Thanks for watching!

[@Hynjia]

I just built a new computer today that can finally do stuff like this. I can put all these fancy components to work with your content! So, thank you!

[@troyvarius8676]

This is phenominal! Thanks so much for all this - I just found your two most recent videos and now I'm going to binge on everything else. Excited!

[@ardkorejunglist]

Hey Mike! Just wanted to show some appreciation for the obsidian ai videos you have been doing, i use this every work day now thanks to your assistance thank you very much! ❤

[@itsjohnmavrick]

Looking forward to the benchmarks to see if it's worth switching from copy pasting to GPT 🤔 thank you for diving deep into LLMs for the Obsidian community!

[@SystemSculpt]

Thanks for the appreciation, love your vids too! An in depth local LLM testing video is going up within the next 12 hrs :D

[@etherhealingvibes]

Yesterday updated textgenerator plugin without issues until now. Great model to make it work on obsidian, to do some note ordering tasks. Great videos Mike.

[@SystemSculpt]

So glad it works so far :) and thanks, many many more to come! Cheers.

[@PabCorz]

Thank you very much. I look forward to a new video in which you explain how to use your own documents (RAG).

[@mmbln]

Nice one! Will try it and see what I can do with it.

[@ayan4688]

Hey Mike! I love Text Generator but it only allows you to use model you choose. Is there a way I can embed my obsidian files into a model like Mistral 7B and make the responses wayyyy more specific

[@valensdsilva]

Hey @Systemscupt. Thank you for this video! I have a use case of capturing project meeting notes in Obsidian via meeting transcripts. I'm looking to get obsidian and Lm studio to summarize meetings for me and also do question answering (RAG) on the historical notes I've captured. How would I have to change your prompts to do RAG on content in my obsidian notebook?

[@SciStone]

it works for me however it only shows the completed text in obsidian, it does not stream each word, what am I missing?

[@GuyJames]

If it comes up immediately it means your computer is powerful enough to not need to stream it.

[@SystemSculpt]

Make sure your "stream" options in Text Generator are both set o enabled. Just search for "stream" when you're in Text Generator settings.

[@neb2777]

same issue for me, even with the streaming settings turned on its still not working

[@JavisJones3DCG]

@@SystemSculpt Hi there! Real dumb question, but for some reason I'm unable to find the setting for streaming in LM Studio (v 02.20). I've looked everywhere in the UI but, no joy so far. Any chance you could point me in the right direction? Thanks in advance!

[@ero1.097]

@SystemSculpt I'm searching for a local AI tool to interact with my Obsidian notes. Do you know of any options? Can this plugin handle that, or is it limited to generating text?

[@pnddesign]

I don't understand why we used the 'GenRelations' template. It works without it.

[@SystemSculpt]

It's for the tomorrow's video - I should have mentioned that it's to be used with the actual testing that will be shown tomorrow. Sorry about that!

[@____________________________.x]

How do I run this just within LMStudio? I load the onsidian vision model, go to chat, select a picture to describe but the response is just "### Comment: ### Response:" scrolling up the screen ?

[@lpanebr]

Hey Mike, everything okay over there? I hope Skynet hasn't awaken with your tests!

[@SystemSculpt]

New upload coming soon ;) always glad to see you comment!

[@CyberXchi]

Y G bro

[@IamNomadSauce]

why the hell are subtitles on this thing? cant watch

[@SystemSculpt]

thanks for the feedback! i've decided to remove the hardcoded subs moving forward :) cheers

[@zidviziouz]

Still waiting for the top contenders ;)

[@Deefail]

This is what I get when I hit generate: "Unexpected endpoint or method. (OPTIONS /v1). Returning 200 anyway"

[@Deefail]

So it waas basically the configuration in LLM studio's Local Inference server that I forgot to turn everything on, and take the 2nd out of 3 links to put in Obsidian. Now it works thanks