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

Amazon Kendra: Enterprise Search Service

aws.amazon.com

Post reply on HN
Print view View original

21–30 of 58 posts

Re: Amazon Kendra: Enterprise Search Service

#21

Post by fiddlewin »

crawdog wrote: post #17

Interesting to see more players joining the market. You can't walk into a large Enterprise and start your search conversation with "Your developers just build ____". Otherwise customer will want to build it themselves. The killer feature I haven't seen with many of these solutions is easy, out of the box integration with internal systems (Atlassian Confluence, JIRA, Remedy, SharePoint, FileSystem, Intranet). When you…

You will need very powerful hardware to deploy the deep learning models on-prem for incremental learning.

And most of the time, while not indexing, the hardware would be sitting there sleeping. Probably not very cost-effective for enterprises.

Re: Amazon Kendra: Enterprise Search Service

#22

Post by citilife »

garysieling wrote: post #11
citilife wrote: post #5

Curious how it compares to my offering: https://insideropinion.com/ The main issue is giving access to documents, which most Enterprise customers do not want to do... Further, most info is in employees heads, not in documentation.

From the demo it looked like an alternate way to search things like corporate portals. I.e. they're trying to improve the search that products like SharePoint provide with some ML integration.

Very similar, it also learns from context of a conversation what is likely in a document, a page, video, audio, etc. This alleviates the need to parse media.

Re: Amazon Kendra: Enterprise Search Service

#23

Post by Aeolun »

cj wrote: post #4

This is cool, but much of the functionality they're demoing isn't available in the preview. See the disclaimer at the bottom of the page: > Kendra’s preview will not include incremental learning, query auto-completion, custom synonyms, or analytics. The preview will only offer connectors for SharePoint online, JDBC, and Amazon S3. It will be limited to a maximum of 40k queries per day, 100k documents indexed, and one…

i.e. the preview is mostly useless for any enterprise...

Re: Amazon Kendra: Enterprise Search Service

#24

Post by hueving »

fiddlewin wrote: post #21
crawdog wrote: post #17

Interesting to see more players joining the market. You can't walk into a large Enterprise and start your search conversation with "Your developers just build ____". Otherwise customer will want to build it themselves. The killer feature I haven't seen with many of these solutions is easy, out of the box integration with internal systems (Atlassian Confluence, JIRA, Remedy, SharePoint, FileSystem, Intranet). When you…

You will need very powerful hardware to deploy the deep learning models on-prem for incremental learning. And most of the time, while not indexing, the hardware would be sitting there sleeping. Probably not very cost-effective for enterprises.

> the hardware would be sitting there sleeping. Probably not very cost-effective for enterprises.

Not to be condescending, but idle hardware isn't even on the radar as far as waste goes in enterprises. An on-prem solution that is idle for 364 days of the year is completely fine for most of these companies.

For the ones that do care, that's what they make virtual machines and over-subscription for if they even care the slightest about that.

Re: Amazon Kendra: Enterprise Search Service

#25

Post by hueving »

jpadkins wrote: post #20
xfalcox wrote: post #9

Damn this is a really expensive alternative to Algolia.

it's internal enterprise search, not site search. harder problem.

Is it? The main difference is additional connectors and access control filters. Both are not really hard from a technology standpoint.

Re: Amazon Kendra: Enterprise Search Service

#26

Post by papito »

aerovistae wrote: post #3

Thank God. Even today it's almost always faster to use Google than a site's search bar. Maybe this will start to change that.

Even Google's Search Appliance wasn't a game changer. Reality check - it's DEAD.

Google disrupted the market by factoring in links into its algorithm, something that is rather meaningless in proprietary context.

Re: Amazon Kendra: Enterprise Search Service

#27

Post by arnocaj »

genS3 wrote: post #18

do they use the elastic fork they did a while ago?

They explicitely mention Question Answering. Could it be that they use something like BERT trained with Squad dataset, and fine tuned on additional content? If so, Bert is very intense in terms of required GPU hardware...

Re: Amazon Kendra: Enterprise Search Service

#28

Post by whitezebra »

Hey HN, we're building a similar product at https://evertrove.co -- we don't have the limits Kendra currently has, and integrate with a lot more services. We're still early and figuring out what the pricing structure should be, but we're making it a lot more competitive than Kendra is.

We'd love to talk to you if you're interested in using Kendra. We're also wondering if there's more value on the Question Answering side of things, or the document retrieval side of things? Would love your thoughts!

Re: Amazon Kendra: Enterprise Search Service

#29

Post by genS3 »

arnocaj wrote: post #27
genS3 wrote: post #18

do they use the elastic fork they did a while ago?

They explicitely mention Question Answering. Could it be that they use something like BERT trained with Squad dataset, and fine tuned on additional content? If so, Bert is very intense in terms of required GPU hardware...

pretty sure they use some of the BERT + rules + a classic search engine + a LOT of marketing kool-aid

Re: Amazon Kendra: Enterprise Search Service

#30

Post by deevin9 »

genS3 wrote: post #19
crawdog wrote: post #17

Interesting to see more players joining the market. You can't walk into a large Enterprise and start your search conversation with "Your developers just build ____". Otherwise customer will want to build it themselves. The killer feature I haven't seen with many of these solutions is easy, out of the box integration with internal systems (Atlassian Confluence, JIRA, Remedy, SharePoint, FileSystem, Intranet). When you…

lucidworks or sinequa are already doing that in the enterprise search space

Coveo is doing it better
Post reply on HN