_vxw6

4 tahun yang laludiscuss

Haha I copied it from that page, hilliarious!

I'll keep it haha

4 tahun yang laludiscuss

It stores it in browser local storage using IndexDB, if you have access to years of documents, it might take up to 10+gb of persistant storage.

_vxw6

4 tahun yang laludiscuss

gb's of storage, potentially 10+ for very large datasets.

Minutes, not days. Very big data sets might take 30+ minutes (or even a couple of hours), but usefulness starts in the first few minutes (because of the priority algorithm)

_vxw6

4 tahun yang laludiscuss

Actually a few hundred documents is really no biggy, my current benchmarks is in the range of <250ms (instant feeling) for hundreds of thousands of paragraphs.

I'm testing this on a large knowledge base.

_vxw6

4 tahun yang laludiscuss

Same bundle of weights but is being run by some rust code that is compiled down to WebAssembly.

_vxw6

4 tahun yang laludiscuss

It will be very soon https://github.com/haystackoss/haystack

some rust code that compiles to WASM loads LLM from memory, and uses custom transformer.py like rust alternative we wrote.

_vxw6

4 tahun yang laludiscuss

Forgive me if I don't understand, but I don't think there's a problem with multiple companies using the same common noun as the base for their domain.

Let the best product be remembered for the name.

_vxw6

4 tahun yang laludiscuss

Not really, gethaystack searches your tabs

_vxw6

4 tahun yang laludiscuss

Sorry didn’t assume otherwise, replied accidentally to the wrong thread

_vxw6

4 tahun yang laludiscuss

Note taken lol wow

_vxw6

4 tahun yang laludiscuss

Thanks

_vxw6

4 tahun yang laludiscuss

I’m planning on releasing an open source version of this.

But also have paid features that managers would like to use.

_vxw6

4 tahun yang laludiscuss

I’m using a fine-tuned t5-small model, I fune-tuned it for two tasks, question answering from a paragraph, and highlighting relevant text of search results.

_vxw6

4 tahun yang laludiscuss

The tricky part is to understand which parts are you indexing, paragraph vs. sentences vs. pages.

But yeah

_vxw6

4 tahun yang laludiscuss

I load the 90mb model into memory from IndexDB, and then some rust code compiled down to WASM does calculations with the model.

_vxw6

4 tahun yang laludiscuss

Hi, didn’t intend to repost this, it’s just that HN is hard to figure out.

And most first posts don’t get the intended traction for various reasons (too long, bad wording, unclear).

reposting and changing the post is totally allowed :)

_vxw6

4 tahun yang laludiscuss

open & free for self hosted version, current alpha version is client side (runs in the browser).

_vxw6

4 tahun yang laludiscuss

You hit the nail on it’s head, some of these is something I’m dealing with right now (i.e dates)

_vxw6

4 tahun yang laludiscuss

Makes me wonder, what kind of information sources do you use at work?

Slack, teams, confluence or notion? airtable? jira?

_vxw6

4 tahun yang laludiscuss

Very good explaination!

hundred of millis is what I experienced.

Submissions

Show HN: I built Haystack – your own google for scattered workplace knowledge

Show HN: I built haystack – Google for workplace knowledge

comments