obsidian-ava VS obsidian-smart-connections

Today we’re going to learn how to build a recommendation system for a social publishing platform like Medium. I wanted to share what I learned building the popular Obsidian plugin AVA that recommends your notes.

I just search Obsidian plugins and there are 3 that might work for you:

- https://github.com/louis030195/obsidian-ava

- https://github.com/brianpetro/obsidian-smart-connections

You can try https://app.anotherai.co which does exactly this

is this a paid service? the github repo is public but links to a paid service or plugin

Hi foks Louis & Ben here.

We just wanted to share Embedbase. Embedbase is an open-source api to easily create, store, and rerieve embeddings.

It started out as an internal api for an Obsidian plugin we developed called [AVA](https://github.com/louis030195/obsidian-ava). We use it in AVA to find similar notes ([see small demo](https://user-images.githubusercontent.com/25003283/213157399...)), but you can potentially use it to do anything that openai embeddings can do.

Right now it's really quite barebones and basically just abstracts the openai embeddings api & pinecone, but we're planning on making it easy to work with whatever database or auth mechanism.

You can have a look at the github repo here:

This plugin might do the trick: https://github.com/louis030195/obsidian-ava. I don`t use it myself, but there is a "Suggest Tags" command.

Obsidian AVA (summarization, write & rewrite)

For my personal notes, I use Smart Connections[1] with Obsidian. I am considering devising my own solution using LlamaIndex[2] in the near future.

For coding, I use Copilot[3]. While it's been great for writing boilerplate code, it falls short in every other regard. I also had the opportunity to try the new version of Copilot as well, but it feels like a glorified ChatGPT inside VSCode.

For everything else, I use a tiny tool I made[4] which enables me to invoke my own prompts in basically any application that allows me to select text.

[1] https://github.com/brianpetro/obsidian-smart-connections

[2] https://gpt-index.readthedocs.io/en/latest/getting_started/s...

[3] https://github.com/features/copilot

[4] https://github.com/overflowy/chat-key

Adding options to us local LLM's like GPT4all, or alpaca #141

Smart Connections allows you to search using embeddings[1].

[1] https://github.com/brianpetro/obsidian-smart-connections

There is actually a plugin that leverages AI to do it. I haven't used it yet plus there might also be a concern over giving a third party AI access to your notes but if you are interested here is the link. https://github.com/brianpetro/obsidian-smart-connections

The "smart connection" plugin is ideal for your search needs. This plugin allows you to search using semantics rather than keywords, just like Google. https://github.com/brianpetro/obsidian-smart-connections

Here is the Obsidian plugin I was referring to: https://github.com/brianpetro/obsidian-smart-connections

I am very attracted to the Smart Connections plugin, which would implement Obsidian with the only real feature I envy other centralized PKMs (such as Mem X): that of finding and connecting to similar notes. The point is this: the price (paid after each use) due to Open AI for using the GPT engine.

I'm using Obsidian with the Smart Connections plugin. I then used chatGPT (4) to write a python script that chatGPT summarized this way:

Smart Connections