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

DataBorg – Knowledge Management Simplified

databorg.ai

Post reply on HN
Print view View original

11–20 of 47 posts

Re: DataBorg – Knowledge Management Simplified

#11

Post by yamalight »

number6 wrote: post #8

If I use the second prompt: "Try our Text To Knowledge Graph API" You have made too many requests. Please login or try again in ~10 seconds. I am Rate limited; maybe implement a cooldown on the submit button or something — feels a bit unfriendly on a landingpage

Hi, CTO of DataBorg here. Thanks for trying it out! And apologies for the mess - we weren't quite ready to go public just yet :)

Current rate-limiting is IP based, so it might be your shared IP public address messing things up. The next update we're rolling out over the next few days should make it less aggressive.

If you login with your github / email - you should be able to try thing out without rate-limiting issues. And if 300 credits is too little - feel free to reach out to me at tim at databorg.ai - I'll set you up with a month of free Hobby tier (that'll be adding soon) :)

Re: DataBorg – Knowledge Management Simplified

#12

Post by yamalight »

dominotw wrote: post #9

I was able to try just one 'entity recognition' with some specious results. Was blocked by second request because i was making ' too many requests'. Bye.

Hi, CTO of DataBorg here. Thanks for trying it out! And apologies for the mess - we weren't quite ready to go public just yet :)

Current rate-limiting is IP based, so it might be your shared IP public address messing things up. The next update we're rolling out over the next few days should make it less aggressive.

If you login with your github / email - you should be able to try thing out without rate-limiting issues. And if 300 credits is too little - feel free to reach out to me at tim at databorg.ai - I'll set you up with a month of free Hobby tier (that'll be adding soon) :)

Re: DataBorg – Knowledge Management Simplified

#13

Post by yamalight »

eurasiantiger wrote: post #7

The ”entity recognition” is absolutely useless. I tried it with a short text describing several entities and their relationships, yet it only spotted the word ”Users”. Not ”company”, not ”account”, not ”subscription”… not exactly impressed.

Named entity recognition is typically used to locate and classify named entities in text. So you'd want to have a text that mentions specific things - companies, people, locations, etc. Abstract things like "account" or "subscription" don't technically fall under "named entities" category.

Re: DataBorg – Knowledge Management Simplified

#14

Post by exotree »

This is really cool! Obviously some work to be done here, and I see the Hacker News bump may have come a bit early even for an MVP!

The more accessible we can make this technology, the better. Best of luck on your journey, and I’ll be sure to check in!

Re: DataBorg – Knowledge Management Simplified

#15

Post by yamalight »

exotree wrote: post #14

This is really cool! Obviously some work to be done here, and I see the Hacker News bump may have come a bit early even for an MVP! The more accessible we can make this technology, the better. Best of luck on your journey, and I’ll be sure to check in!

Thank you! :)

Re: DataBorg – Knowledge Management Simplified

#16

Post by always2slow »

yamalight wrote: post #6
yawnxyz wrote: post #3

This looks super neat and incredibly useful, but the pricing is an absolute non-starter. I'll definitely use more than the free tier, and the next paid tier is 3000 API requests for $300 per MONTH? Am I alone in thinking this is way too expensive? "$300 per month for small projects" makes me feel like I'm extra poor or something.

Hi, CTO of DataBorg here. Thanks for trying it out! We weren't quite ready to announce it to public just yet :) But hey, can't do much about it now. Pricing is still a placeholder basically. We want to be in line with industry (which is generally ~0.001$ per 1000 characters), so the final tiers would look something like this: Free - 3,000 credits Hobby - 50,000 credits / 49$ Pro - 300,000 credits / 299$ Business - 5,…

No post body was provided.

Re: DataBorg – Knowledge Management Simplified

#17

Post by drooby »

always2slow wrote: post #16
yamalight wrote: post #6

Earlier quoted context omitted.

Hi, CTO of DataBorg here. Thanks for trying it out! We weren't quite ready to announce it to public just yet :) But hey, can't do much about it now. Pricing is still a placeholder basically. We want to be in line with industry (which is generally ~0.001$ per 1000 characters), so the final tiers would look something like this: Free - 3,000 credits Hobby - 50,000 credits / 49$ Pro - 300,000 credits / 299$ Business - 5,…

Quoted post unavailable.

Not cool

Re: DataBorg – Knowledge Management Simplified

#20

Post by lumost »

yamalight wrote: post #10
lumost wrote: post #4

Cool product, I ran out of free requests before I could try the knowledge graph API. Out of curiosity have you thought about how someone would use this product? is the idea that you would use it to organize information in a CRM or similar product? One interesting use case I heard from an SMB real estate agent was that they needed an assistant to organize customer details, send emails, and make appointments. As one ca…

Hi, CTO of DataBorg here. Thanks for trying it out! We weren't quite ready to announce it to public just yet :) But hey, can't do much about it now. Pricing is still a bit of placeholder - there'll be 10x more credits on free tier soon-ish. There is quite a number of ways you could utilize named entity recognition (NER) and/or knowledge graphs (KGs). Ranging from extracting mentioned entities (to e.g. provide a quick…

Got it, so the pitch is to provide a building block to help others build knowledge graphs. Do you see substantial uptake of knowledge graphs in industry? many of the examples I've seen historically either propose building a knowledge graph for the sake of a knowledge graph. Or work on a particular product which lends itself to knowledge graphs such as Question and Answering.

Coming from someone who's worked in NLP for a number of years.

Post reply on HN