DataBorg – Knowledge Management Simplified
databorg.aiThis 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 - 5,000,000 credits / 4999$
If you could email me privately at tim at databorg.ai, I could give you a free month of hobby tier as apologies for this mess :)
edit: formatting
Ooo that pricing is much better for indie hacking, thanks for explaining!
Happy to clear the misunderstanding :)
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) :)
Iam infact behind a Carrier-Grade-NAT so this could mess things up.
Thanks for your reply!
Just noting the same thing here for me, I tried looking at an example and it failed with this error. I think I would not even hit the API for the examples, just show it. My 2 cents.
Thanks for feedback! I'll indeed be adjusting examples to always return results as was suggested here.
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! :)
Oh boy. The ol "wasn't ready for HN" problemo. Good luck with that one! Cool product of course. ;)
I got following error after trying the demos on the homepage
“You have made too many requests. Please login or try again in a few seconds.”
You might think about adding exception for your domain or the sample text you provide.
I've lowered the rate-limiting to 1s, so it should be less of an issue now. But I like the idea of adding examples to exceptions, thanks!
Thank you :D
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 can imagine such a gig isn't great for the employee as there isn't much career path in the long run.
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 access to all articles containing specific entity), to semantic search, to building a unified knowledge graph from text (unstructured) data you have. Cool thing about KGs is that they are based on open standards, so once you've built them out of the data you have - there's quite a few existing tools that (for the most part) work out-of-the-box with them.
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.
Yep, that'd be the pitch! In the beginning we'll just provide API for people who know what they need / want. Later on the plan is to have "all-in-one" products for end users directly (but that'll take time).
On KGs and industry - as far as we are aware, they are quite widespread. Most of fortune 500 companies use KGs in some form. QA is definitely one of the applications. There's also been quite a bit of work done on e.g. explainable AI using KGs lately (one of the areas we're working on as well).
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) :)
Is this built off of https://huggingface.co/Babelscape/rebel-large ? It's shared under cc-by-nc-sa-4.0 Doesn't nc stand for non-commercial? "Non commercial share alike - Redistribute, revise, remix using the same license as the original for non commercial use only". Looks like you're in violation of this license.
We have our own custom datasets, models and code we've used to train them. REBEL can be considered "prior art" though :)
how do you identify that it might be built off that?
They forked it on their github which is linked from their landing page: https://github.com/orgs/DataBorg/repositories
edit: also https://github.com/DataBorg/wikineural which has a non-commercial license as well. Does HN like to see this kind of discussion here?
Same with Wikineural - it's a great project, but falls under "prior art". We have our own custom datasets / models / code for NER as well.
Prove it.
Edit: to be clear i'm not buying this for a second. Your 1st demo produces the exact same output as Babelscape/wikineural-multilingual-ner demo. If you built off of their model you need to abide by their license of non-commercial use and share-alike. I think you're a bad actor and I can't believe HN is leaving this up. Your company name also has negative implications: https://en.wikipedia.org/wiki/Borg
So, er, how exactly would I prove it? Do you want me to share our code / db / etc we've worked on for past ~two years? :)
For one - how many wikidata classes exactly do you get from Wikineural? If I remember correctly, it can do four (person, location, organization, other). Our models do several thousands.
It'll likely annotate similar things in text since our model is also transformers-based (which is basically current state of art) - can't really do anything about that.
edit: phrasing.
Yes? I think my stance is very clear. It appears that you have forked some opensource models and built proprietary software off of them which you are now trying to profit, against their licenses.
German company, not even a basic imprint == red flag.
That is something we'll be adding shortly. It's not there yet since we weren't quite ready to go public yet.
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.
So what good is the algorithm for knowledge management in IT if it cannot handle abstraction?
Can you show an example of the text you was trying to extract entities from, interested to see the problem.
I didn’t save it, but it was a generic specification text much like this one, but longer and more detailed and nuanced:
Users have personal user accounts. Each user account can belong into multiple companies. Each company can assign users access rights to system services according to predefined roles. Each system service has a unique identifier as well as one or more service group identifiers and namespace identifiers.
DataBorg extracts data from text and builds a knowledge graph from it.
Looks interesting, but no info on what the 4000 classes are, is the ontology available?
We're using top level wikidata classes (you can see specific classes in JSON response). Full list is not published yet, but will be available in the near future.