ObsidianMD

4688 readers

13 users here now

Unofficial Lemmy community for https://obsidian.md/

founded 2 years ago

MODERATORS

grabyourmotherskeys@lemmy.world

Pexily@lemmy.world

i know i mention this but maybe i didn't tell directly - obsidian vaults can easily be used for RAG allowing you to explore your notes in new ways. the extract_wisdom pattern from (soc.kvet.ch)

submitted 1 month ago by emory@soc.kvet.ch to c/obsidianmd@lemmy.world

10 comments fedilink hide all child comments

i know i mention this but maybe i didn't tell @obsidianmd directly - obsidian vaults can easily be used for RAG allowing you to explore your notes in new ways. the extract\_wisdom pattern from #fabricAI is great also.

actually here's an extension i came across this morning that can use Fabric's patterns:

https://github.com/chasebank87/mesh-ai

#meshAI #AI #PKM

you are viewing a single comment's thread
view the rest of the comments

[–] mitch@hoagie.cloud 1 points 1 month ago (2 children)

@emory @obsidianmd i will be honest that is a question you might be more equipped to answer than i, but here are the links if you wanna check it out. i see it has a folder named LLMproviders, but i am not sure if that is what you mean or not.

obsidian://show-plugin?id=copilot

https://github.com/logancyang/obsidian-copilot

https://github.com/logancyang/obsidian-copilot/tree/master/src/LLMProviders

[–] emory@soc.kvet.ch 1 points 1 month ago (1 children)

@mitch @obsidianmd this extension is great and i wish others used it instead of reimplementing things https://github.com/pfrankov/obsidian-ai-providers

[–] INeedMana@piefed.zip 1 points 1 month ago (1 children)

Any chance for something like this working with Le Chat/Mistral? I don't see it in readmes

[–] emory@soc.kvet.ch 1 points 1 month ago

@INeedMana if they offer an OpenAI-ish compatible API (e.g. https://blahblah/v1) you can add it as an OpenAI service with a new endpoint and your own API creds inside AI Providers but IDK about the various other extensions.

the mesh-AI one uses fabric though and you can configure fabric to use mistral's API just fine i reckon?

[–] gabek@social.gabekangas.com 0 points 1 month ago (3 children)

@mitch @emory @obsidianmd Do you pay for it?

[–] mitch@hoagie.cloud 1 points 1 month ago

@gabek @obsidianmd @emory I do not. It seems to function with all the features when you use local inferencing via Ollama.

[–] emory@soc.kvet.ch 1 points 1 month ago

@gabek @mitch @obsidianmd i don't either, i have other ways of doing what the paid version supports. i use cloud foundation models and local; my backends for embeddings are always ollama, lmstudio, and/or anythingLLM.

#anythingLLM has an easily deployed docker release and desktop application. it's not as able in managing and cross-threading conversations as LM (really Msty does it best) but #aLLM has a nice setup for agents and RAG.

[–] emory@soc.kvet.ch 1 points 1 month ago

@gabek @mitch @obsidianmd some of the small models i like using with obsidian vaults locally are deepseek+llama distills and MoE models for every occasion. fiction and creative, classification and vision. there's a few 8x merged models that are extremely fun for d&d.

i have a speech operated adventure like #Zork that uses a 6x MoE that can be really surreal.

there's a phi2-ee model on hf that is small and fast at electrical eng work, i use that for a radio and electronics project vault!