[HN Gopher] AlloyDB AI: Generative AI applications with PostgreSQL
       ___________________________________________________________________
        
       AlloyDB AI: Generative AI applications with PostgreSQL
        
       Author : jerryjerryjerry
       Score  : 77 points
       Date   : 2023-08-29 19:16 UTC (3 hours ago)
        
 (HTM) web link (cloud.google.com)
 (TXT) w3m dump (cloud.google.com)
        
       | xnx wrote:
       | Very cool that there's a "preview" downloadable version:
       | https://cloud.google.com/alloydb/omni
        
       | jadbox wrote:
       | Is/will AlloyDB be open source?
        
         | cheeseface wrote:
         | No, it's Google's proprietary product meant to lock you into
         | their Cloud offering.
        
           | slig wrote:
           | "Free while in developer preview, check back in the future
           | for pricing". Too weird for me.
        
             | viscanti wrote:
             | After that you'll be able to pay for it for a year or two
             | until they realize that running a business is a whole thing
             | and then they'll just deprecate it and kill it off.
        
           | yumraj wrote:
           | As another person noted, there's a downloadable version at:
           | 
           | https://cloud.google.com/alloydb/omni
        
             | hmottestad wrote:
             | "Available at a fraction of the cost of legacy databases,
             | with a free developer edition"
             | 
             | So I guess there is some kind of licensing model even
             | though you can download it and run it on your own servers.
        
               | yumraj wrote:
               | Yes, perhaps there is a free developer edition, but for
               | commercial deployment you have to use their cloud. That'd
               | be a bummer..
        
               | formercoder wrote:
               | Disclaimer: I work on Google Cloud
               | 
               | Yes it's commercial but you can run it on any cloud or on
               | prem.
        
       | mpercy wrote:
       | How are people actually using vector databases?
       | 
       | The closest explanation to a use case architecture I've seen
       | recently was https://mattboegner.com/knowledge-retrieval-
       | architecture-for... - it basically describes doing knowledge
       | retrieval (keyword parsing) from LLM queries, feeding that to a
       | vector db to do similarity search to get a top K similar
       | documents to the parsed keywords, then feeding that list that
       | back into the LLM as potential useful documents it can reference
       | in its response. It's neat but it seems a bit hacky. Is that
       | really the killer app for these things?
        
         | ultra_nick wrote:
         | Yes, GPU poor people are just using top k semantic search to
         | try to fix the issues will low ram low knowledge LLMs. It's OK
         | for some applications, but other methods need to be
         | investigated.
        
         | CharlieDigital wrote:
         | We used it in an e-commerce application.
         | 
         | Apparently, one of the hardest things to do is to match a
         | product name + description to a product taxonomy.
         | 
         | There are multiple taxonomies. Here's Google's for example:
         | https://www.google.com/basepages/producttype/taxonomy.en-US....
         | 
         | Amazon has their own. Walmart has their own. Target has their
         | own.
         | 
         | Given a list of tens of thousands of products, how can you
         | automatically match the product to a merchant's taxonomy?
         | 
         | I started with a "clever" SQL query to do this, but it turns
         | out that it's way easier to use vector DBs to do this.
         | 1. Get the vector embedding for each taxonomy path and store
         | this          2. Get the vector embedding for a given product
         | using the name and a short description         3. Find the
         | closest matching taxonomy path using vector similarity
         | 
         | It's astonishingly good at doing this and solved a big problem
         | for us which was building a unified taxonomy from the various
         | merchant taxonomies.
         | 
         | You can use the same technique to match products with high
         | confidence across merchants by storing the second vector
         | embedding. Now you have a way to determine that product A on
         | Target.com is the same as product A' on Walmart.com is the same
         | as product A'' on Amazon.com by comparing vector similarity.
        
       | whimsicalism wrote:
       | > AlloyDB AI allows users to easily transform their data into
       | vector embeddings with a simple SQL function for in-database
       | embeddings generation, and runs vector queries up to 10 times
       | faster than standard PostgreSQL. Integrations with the open
       | source AI ecosystem and Google Cloud's Vertex AI platform provide
       | an end-to-end solution for building gen AI applications.
       | 
       | - Embrace [X]
       | 
       | - Extend [X]
       | 
       | - Extinguish [?]
       | 
       | Will they allow it to use custom embeddings?
        
         | insanitybit wrote:
         | lol couldn't you say that Postgres is EEE for SQL? It embraced
         | SQL, has added new functions and incompatible constructs to
         | SQL... is it going to extinguish SQL next?
        
           | TexanFeller wrote:
           | It does provide plenty of PG specific capabilities, but PG
           | has always had much better conformance to SQL standards and
           | support for all the standard features than other DBs like
           | MySQL. It's one of the most compatible DBs from a few points
           | of view.
        
             | insanitybit wrote:
             | Yes, that's the "embrace" part.
             | 
             | I guess my point is that "Embrace, Extend, Extinguish" is a
             | really outdated saying and I hate it. Embracing and
             | Extending are really good things.
        
               | derefr wrote:
               | The "Extend" stage is the key: it's actually supposed to
               | refer to attempts to introduce "better" / "more
               | advanced", but _proprietary_ and _inherently
               | implementation-locked_ technologies into an
               | implementation (and thus into the platform the
               | implementation implements); where these technologies don
               | 't complement, but instead _supersede_ the use of the
               | platform 's existing open-standards capabilities, for
               | those using this implementation.
               | 
               | In the "Extinguish" stage, the open-standards
               | capabilities are then _deprecated_ in favor of these
               | proprietary technologies -- in theory just for the
               | implementation itself, but in practice ecosystem-wide,
               | due to the implementation 's majority user share. As the
               | locked-in nature of the component makes it impractical to
               | offer any other implementations of it, all other
               | implementations "fall behind" due to lacking this
               | component, supporting fewer and fewer greenfield
               | projects, until users give up on them, "Extinguishing"
               | their market-share.
               | 
               | The "Extinguish" stage only makes sense insofar as the
               | technologies introduced in the "Extend" stage _have_
               | inherent implementation lock-in. Otherwise, it 's just a
               | regular open-standards dueling-RFC-banjos scenario, not
               | EEE.
               | 
               | With Internet Explorer, the "Extend" phase was when
               | Microsoft attempted to get people to write ActiveX
               | components (that could only ever possibly work on
               | Windows, since the ActiveX "platform API" is just "the
               | entire Windows API") instead of writing JS. If doing this
               | had become popular, no website that did it would have
               | worked on any other browser than IE (and so there would
               | have had to be "the ActiveX-enhanced IE version" and "the
               | regular HTML version" of the site. Which _was_ actually a
               | thing for a short while... though only on Microsoft 's
               | own web services, AFAIK.)
        
           | thewataccount wrote:
           | I think what you're trying to say is that just because
           | someone - especially [large company] - tries to
           | improve/integrate popular open projects doesn't mean it's
           | always EEE.
           | 
           | Which I doubt EEE is purposeful the majority of the time
           | initially, even if has the potential to become that later. In
           | the case of google I think this would be a case of "how do we
           | add value to our product to sell" followed by "this feature
           | costs us too much resources to maintain, let's cut it and
           | focus on [new feature]"
           | 
           | That being said Postgres is not a good example because AFAIK
           | they're both not a commercial entity (or any registered
           | entity at all?) and they're true FOSS. At the moment they
           | have no commercialization strategy (sponsorships maybe?) and
           | no ability to extinguish anything given their open license
           | and lack of any proprietary services.
        
         | slig wrote:
         | It's not like Google is famous for dropping projects.
        
       | thatcherthorn wrote:
       | > AlloyDB AI allows users to easily transform their data into
       | vector embeddings with a simple SQL function for in-database
       | embeddings generation
       | 
       | Slick!
        
       | hn1986 wrote:
       | Is AlloyDB basically like Aurora DB for AWS?
        
         | bearjaws wrote:
         | Yeah its closest analogy is Aurora, but no serverless option,
         | payment is per vCPU, memory, and storage.
        
           | xnx wrote:
           | Is Google Cloud SQL a more direct alternative to Aurora? I'm
           | having a hard time keeping all these database services
           | straight.
        
             | grrywlsn wrote:
             | Cloud SQL is RDS; AlloyDB is Aurora.
        
         | Keyframe wrote:
         | on steroids it seems
        
         | jerryjerryjerry wrote:
         | Architecturally yes but with an extension of in-memory columnar
         | format as well. This makes it an HTAP (Hybid Transactional and
         | Analytical Processing) database.
        
       ___________________________________________________________________
       (page generated 2023-08-29 23:02 UTC)