from Hacker News

Amazon Kendra: Enterprise Search Service

by garysieling on 12/3/19, 6:26 PM with 55 comments

• by crawdog on 12/3/19, 7:42 PM

  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 have a SaaS search engine it's difficult to export that data... Even worse to secure it. Ironically, Plumtree Software (bought by BEA -> Oracle) had all of this in their product in 2001. What's old is new again... Those features are prime for a comeback.

  I think this is a space where Elastic can do well with an on-prem or managed cloud offering that is "behind the firewall", integrated with customer's environment. Add in term vector search support, ML for document/query understanding, and integration with customer's security model (Active Directory) and it would be compelling.

• by whitezebra on 12/3/19, 9:07 PM

  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!

• by MediumD on 12/3/19, 9:27 PM

  Shameless Plug Alert

  Building a similar enterprise search product at http://landria.io/ that has a lot of additional features & enhancements over a unified keyword index + ML.

  We also have a terraform config if you would like to boot it up within your own private cloud!

  Any feedback would be great appreciated

• by cj on 12/3/19, 7:09 PM

  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 index per account.

• by msoad on 12/3/19, 9:32 PM

  I've worked with setting up Google Cloud Search. GCS is good for our use case because all of our employees use Google G Suite for email calendar and one-off sites. However it took 2 years for it to be somewhat mature enough for us to actually deploy it. We're still missing connectors for some major data sources like Slack.

  Hopefully Amazon moves faster and offers more out of the box data sources. They are missing G Suite content that a lot of orgs are relying on these days. Would be interesting to see what's their strategy there.

• by tchalla on 12/3/19, 7:26 PM

  Probably this dictionary definition of Kendra (kendră) might make sense in this context

  kendra (IndE)

  noun C

  a centre for some activity (research, study, business, art, etc.)

• by citilife on 12/3/19, 7:16 PM

  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.

• by aerovistae on 12/3/19, 7:09 PM

  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.

• by CodeSheikh on 12/3/19, 7:34 PM

  So the idea is I feed all of the content for my website to Kendra (hosted in cloud) and whenever a user performs a search on my website, Kendra will return results to me via a REST(?) call and I can display sorted results back to the user, right? Is the index going to live locally within my ecosystem for faster retrieval of results and Kendra can do updates to the index via some push mechanism? To be honest instead of bootstrapping a solution with Lucene/SOLR-esque, this might be not be bad idea to ride your search on the shoulders of Amazon AI search giant.

• by davchana on 12/4/19, 2:06 AM

  I do not know if it is inspired or not,and my 2G internet is not that fast to open this page, but name Kendra means Center in Hindi, with exact spelling

• by joeAtBiome on 12/4/19, 4:25 AM

  Hello everyone at HN! The team @ Biome (https://www.trybiome.com) is building a unified search platform for finding and organizing internal information. Biome integrates with your existing SaaS applications (Github, Slack, etc.) to surface content no matter where it’s stored.

  If you are interested in a search solution like Biome, please feel free to reach out so we can talk more and learn the best way we can empower your team to be more productive.

• by collsni on 12/4/19, 5:00 AM

  Sure are alot of product plugs going on in the comments.

• by stepstep1 on 12/4/19, 6:18 PM

  Is Kendra just a wrapped Elasticsearch? Initial offering doesn't look like much, only thing "new" is FAQ.

• by hooloovoo_zoo on 12/3/19, 7:20 PM

  It would be cool if they added this to their Kindle e-readers so you could could perform better searches of your library.

• by stepstep1 on 12/4/19, 6:19 PM

  Is Kendra just a wrapped ES ? Only thing novel is FAQ creation and the data sources.

• by lovelearning on 12/4/19, 6:52 AM

  Coming from a Solr/Lucene/Algolia background, my opinions on this:

  What's good:

  ==========

  - Focused search for question and answer databases (such as customer FAQs)

  - ML-based semantic search without requiring any explicit configuration

  - Connectors for S3, AWS-hosted MySQL/PG, Sharepoint. Searching data already in the AWS ecosystem (S3, Aurora) is now easier, and likely faster and cheaper too in some aspects like saving incoming/outgoing bandwidth

  - Document-level access control at all pricing plans

  - Managed search (similar to Algolia)

  What's similar to existing search systems (Solr / ES / Algolia):

  ==========

  - Indexing: All data has to be processed into "field:value" structure prior to indexing

  - Indexing file formats: Plain text, HTML, PDF, MS DOCX, MS PPT

  - Searching: Usual boolean filters and faceting but only at field level.

  - Searching: Field and value boosts for relevance, but only at index-time

  - Results: Highlighting support

  What's missing:

  ===========

  - No multi-lingual support. Only English. Given that it's AWS, I'm very surprised by this actually (or I've missed out something in their docs)

  - Can't configure text analysis for English. I feel this'll return relevant results for formal-style content, but probably not for informal-style content like emails.

  - No connectors for common internal systems: Outlook, JIRA, Confluence

  - No built-in support for CSV, XLS, JSON (that one's odd!). They'll all require preprocessing which means additional infra costs.

  - Doesn't seem to support range- / query- facets. I feel lack of range facets is a big problem, especially for numerical data.

  - No query-time relevance tuning

  - No field-level access control

  - Scores are not returned in results

  - Common post-searching functionality is missing: rescoring, grouping, clustering

  What's unknown:

  ============

  - I don't see any information about phrase or proximity searches. Of course, they are usually relevance hacks in keyword-based systems, but sometimes users really need exact phrase matches. Does their ML backend handle this somehow?

  - All search systems fall short while handling proper nouns - names, places, things, scientific names. It's possible to alleviate it to some extent using part-of-speech aware indexing. Not sure if Kendra does it in its ML backend.

• by xfalcox on 12/3/19, 7:22 PM

  Damn this is a really expensive alternative to Algolia.

• by mlboss on 12/3/19, 7:35 PM

  What kind of technology they might be using for this ?

• by vkaku on 12/4/19, 6:28 AM

  Where's the AWS Kitchen Sink Service? :)

• by genS3 on 12/3/19, 7:43 PM

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