Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I used GPT to build a search tool for my second brain note-taking system

reasonabledeviations.com

Post reply on HN
Print view View original

51–60 of 103 posts

Re: I used GPT to build a search tool for my second brain note-taking system

#51

Post by mtnygard »

DanielVZ wrote: post #36
abrkn wrote: post #32

I’d love to have a ChatGPT that was also trained on all of the pages from my “second brain,” Roam Research. Imagine, I could ask it questions about myself, my friends, and my business. It would in many ways know me better than me from reading all my journal entries. How many years are we away from something like this?

Zero. I’ve done this with google drive and GPT-3 (thus quite limited in prompt length). The biggest hurdle for your requirements is the nonexistent public API for ChatGPT and Roam Research.

Not sure if this is still supported, but Roam used to have an in-app query interface. You could use the JS console to run Datomic style Datalog queries.

Re: I used GPT to build a search tool for my second brain note-taking system

#52

Post by cratermoon »

alostpuppy wrote: post #46
cratermoon wrote: post #43

Earlier quoted context omitted.

I just put my notes into ElasticSearch and use the TextAnalysis processor and get a lot of the same functionality.

This is interesting. How effective was this?

ElasticSearch's text analyzer isn't semantic, but it does stemming and a few other transformations. Combined with the ranking of results by match, I can type in a couple of words or short phrase and get back a reasonable set of notes. That combined with the tags I used and linking means I can typically find the most relevant notes pretty quickly. It might be nice to have some ability for it to match synonyms of search terms given, eg. 'movie' and 'cinema'. I worry about overzealous collapsing of synonyms, for example 'film' can mean 'movie', but mostly they are different concepts.

Re: I used GPT to build a search tool for my second brain note-taking system

#53

Post by senectus1 »

alostpuppy wrote: post #45
senectus1 wrote: post #33

Earlier quoted context omitted.

MS is very close to this. they have chatGPT listening to meetings and taking notes then adding tasks to attendee calendars...

Link? Because I’m gonna need this.

they lightly cover it in this blogpost https://www.microsoft.com/en-us/microsoft-365/blog/2023/02/0...

but I've seen more detailed capability... I can't remember if It was under NDA though. I cant seem to find it with a quick search though

Re: I used GPT to build a search tool for my second brain note-taking system

#54

Post by sixstringtheory »

tomjakubowski wrote: post #49
haswell wrote: post #47

Earlier quoted context omitted.

The way I read this, in a world with machines that can travel at high speeds, people still watch professional runners because they are interesting to watch, and we’re inspired by human achievement. For similar reasons, it doesn’t really matter that computers are better at chess than us.

The cool thing I think is that we watch both, running and race cars.

Also, I can drive my car to get places quickly, but sometimes I enjoy cycling or walking instead because it allows me to take in my surroundings more fully at the slower pace, and the exercise makes me feel good.

Re: I used GPT to build a search tool for my second brain note-taking system

#55

Post by cjohansson »

tomjakubowski wrote: post #49
haswell wrote: post #47

Earlier quoted context omitted.

The way I read this, in a world with machines that can travel at high speeds, people still watch professional runners because they are interesting to watch, and we’re inspired by human achievement. For similar reasons, it doesn’t really matter that computers are better at chess than us.

The cool thing I think is that we watch both, running and race cars.

Yes but humans are required (as runners or drivers) to make it interesting to watch. Humans are human-centered by nature (of course)

Re: I used GPT to build a search tool for my second brain note-taking system

#56

Post by lynx23 »

pessimist wrote: post #27
michaericalribo wrote: post #5

These "augmented intelligence" applications are so exciting to me. I'm not as interested in autonomous artificial intelligence. Computers are tools to make my life easier, not meant to lead their own lives! There's a big up-front cost of building a notes database for this application, but it illustrates the point nicely: encode a bunch of data ("memories"), and use an AI like GPT to retrieve information ("remembering…

In chess we had a tiny window of a few years when humans could use the help of computers to play the world's best chess. By 2000, computers were far better than humans and the gap has increased. Chess players are now entertainers, like all us humans are destined to spend our time doing.

Well, isn't that true for most skills which have been suplemented by technology? In fact, if you look at the handcrafting bussiness, hand-made is now a selling point. Like someone prefers a product to be handmade, others will prefer watching a game of chess between two humans. Just because machines are better at something doesnt mean that humans have become useless. Its just a question of the point of view, IOW, how depressing you want to see the world.

Re: I used GPT to build a search tool for my second brain note-taking system

#58

Post by bongoman37 »

DavidPiper wrote: post #15
michaericalribo wrote: post #10

Earlier quoted context omitted.

Imagine a model that decides on its own to assert the Fifth on your behalf. But now imagine that AI decides to lock you out of your own system...

We already have those. They're called Google, Microsoft and Apple.

[dead]

Re: I used GPT to build a search tool for my second brain note-taking system

#59

Post by gk1 »

leobg wrote: post #28
dchuk wrote: post #26

Earlier quoted context omitted.

When using SBERT instead of gpt for this use case, is it paired with some sort of vector database or just all done in code/memory?

You’d want persistence, since the embedding process takes some time. But you don’t need to go all Pinecone on this. There is FAISS, and there is hnswlib, for example. Like SQLite for vector search.

Friendly reminder that we (Pinecone) have a free tier that holds up to ~5M SBERT embeddings (x768 dimensions). For quick projects, going "all Pinecone on this" could turn out to be the easier and faster option.

Re: I used GPT to build a search tool for my second brain note-taking system

#60

Post by ramblerman »

trane_project wrote: post #25

I've been thinking of using GPT or similar LLMs to extract flashcards to use with my spaced repetition project ( https://github.com/trane-project/trane/ ). As in you give it a book and it creates the flashcards for you and the dependencies between the lessons. I played around with chatgpt and it worked pretty well. I have a lot of other things in my plate to get around first (including starting a math curriculum) but…

Every now and again I come across a real gem on here. Love trane and the idea behind it, can't wait to play with it after work.
Post reply on HN