Show HN: A unified cloud drive with AI search for your files, photos, bookmarks | Hacker News Reader

Show HN: A unified cloud drive with AI search for your files, photos, bookmarks

fabric.so

4 pointsjohnnymakes5 comments

Hi HN,

Today we’re launching Fabric – an internet drive that combines varied data-types (bookmarks, files, notes, images & more) into a single home, with AI-powered semantic search, so a user can find anything again in their own words.

Without Fabric, this data would scattered across different stores and the user is burdened with finding the right item in the right store (often via brute force chronological scrolling in a file browser, when they cannot remember the precise name of the file/document).

Because Fabric turns everything into a universal object, users are able to attach annotations to them, which provide context on why the content was important when the user returns to it. The annotations also form part of a collaboration surface, where conversations can happen on top of objects.

We are also able to represent that data reliably overlaid on top of websites, if that's what the data object references – e.g. an image on a specific webpage will show the Fabric annotations that were attached to it.

We're focused on researchers and users that perform discovery and inspiration gathering tasks, which in Fabric they can do solo or together.

We still have a long way to go and would love to hear your feedback.

Open articleView on HN

If you are ranking documents based on KNN-style algos against document embeddings, how do you deal with more intentional search queries that have a narrow intent to retrieve a specific type of content?

If I browse around and save content to your app, I might want to retrieve this exact piece of content and not any other one that may be semantically close to the query. My experience with vector-based systems (and let's be honest, we are really talking about a recommendation system rather than a search algo here) is that they are hard to combine in a way that is conducive to efficient information retrieval.

You search for a "dog" and you get "cats" because they are similar, but maybe I really want "dog" and not "cat". I find that tremendously inconvenient when apps force you into semantic search and don't let you choose. Sure that might increase the recall, but still please let me choose.

We break the 2 types out in the UI, listing separately. So the user gets to choose. This gives a kind of "best of both worlds" outcome, where a user never gets zero results (and can be make very low fidelity queries), but also doesn't have to sacrifice specificity when the query they're making is one of precision and intentional retrieval.

Can you add abstract extraction or something for papers from the arXiv?

What I personally need is not really highlighting and all that, but more like advanced bookmarking with search on top to let me retrieve stuff by topic (more or less). If we could just bookmark them, have the abstract extracted and made searchable through semantic search, that would be cool

Since Notion excels in collaborative workspaces, could you elaborate on how Fabric sets itself apart when it comes to real-time interactivity, hierarchical content organisation, and overall user experience?

It's a reasonable question: in short, Notion is note and notebook centric – everything falls into one of these 2 categories.

Our structuring is that there are objects and wrappers, but we aren't so prescriptive on what these things have to be exactly... but an object could be a note.

So we're more of a filesystem that supports notes, rather than a notebook that can host rich media.

Reply on news.ycombinator.com