Explain the problem as you see it
For research and writing I should be able to quickly see related nodes, not just by exact wording or linking, but by related topics and including nodes that I perhaps had forgotten or didn't realize were related.
Why is this a problem for you?
Using AI Embeddings to surface related notes is now a priceless part of my workflow that I can currently only do in other apps. The amount of time savings is huge and the quality of my work has gone up considerably, including being able to make serendipitous connections that I never would have otherwise. I want to do this in Tana.
Suggest a solution
Embed and store embeddings for each node in a workspace and include a section at the bottom of each page, near the references section, to show the top 5-10 similar nodes.
8 Comments
Hey Sarah! Could you elaborate on how does it look like in practice?
I'm hoping it would work exactly like the Smart Connections plugin for Obsidian (https://github.com/brianpetro/obsidian-smart-connections) or like Mem.ai's similar mems.
When I navigate to a node, Tana would automatically display the top similar nodes in a section at the bottom.
This would be really valuable.
Those embedings must be multi-language, like the ones from Cohere
Oh this would be so amazing! Especially, if it was possible to prioritize nodes with the same (or related) supertags.
Imagine opening a node for a meeting, and seeing related meetings with similar agenda, or tasks, or discussion items.
Or opening a node tagged with #Flight, and see nodes related to the same trip.
Or opening a #book node, and seeing book nodes with similar content..
Just as when you are about to input a new idea here, the website suggests pre-existing ideas that may be about the same thing, when you tag a new node in Tana, it should make me realize I already have an existing similar tagged node elsewhere in my graph.
The ability to AI search / 'chat with my notes' (i.e. search my notes by semantic meaning using vector embeddings) is the single most helpful feature Tana could build IMO.
I respect how hard it is to prioritise features, and I'm sure the team talked at length with the community when deciding to prioritise the meeting agent, but I personally have very little need for it. This feature instead would be the killer one for me personally. I wonder if the legibility of the solution means few people explicitly ask for this, but I suspect it is a feature that drives many many acquisitions for mem and the others that support it.
I'm honestly, baffled that this isn't higher in requests. Not that this is a needed feature per se, but rather that it's such an obvious extension of Tana.
Two years ago when Tana came out, my understanding was that this was the projected direction of things; that this was essentially what set Tana apart. Tana didn't build supertags so we could all have fun adding unnecessary details to everything. I was under the impression that Tana was built with the coming importance of AI in mind and that supertags were an important feature because they added context to the connections between nodes which would allow the AI to be more informed on not just the fact that two things are related but how they are related.
So to provide that valuable context to the AI it seems only obvious that the next step would be to use that to then project possible connections between nodes. This solves two enormous problems from pkm systems:
This feature is probably one of the most valuable features Tana could create. And Tana is in a better position to achieve this than the hit or miss "related content" that Mem, Reflect Notes, etc offer, because Tana has more structured data and context.
I hope to see this feature soon. And I hope to see more people in the community talking about the value of this. It's really a make or break feature for the future of the app, IMHO.