• jamesrr39 6 hours ago

    Genuine question: I appreciate the comments about MongoDB being much better than it was 10 years ago; but Postgres is also much better today than then as well. What situations is Mongo better than Postgres? Why choose Mongo in 2025?

    • rudolph9 2 hours ago

      Don’t choose Mongo. It does everything and nothing well. It’s a weird bastard of a database—easily adopted, yet hard to get rid of. One day, you look in the mirror and ask yourself: why am I forking over hundreds of thousands of dollars for tens of thousands' worth of compute and storage to a company with a great business operation but a terrible engineering operation, continually weighed down by the unachievable business requirement of being everything to everyone?

      • beAbU 5 hours ago

        Mongo is Web scale.

        • leowoo91 4 hours ago

          instagram use postgresql and still web-scale (unless this was satire)

      • koakuma-chan 5 hours ago

        Choose Mongo if you need web scale.

        • threeseed 5 hours ago

          a) MongoDB has built-in, supported, proven scalability and high availability features. PostgreSQL does not. If it wasn't for cloud offerings like AWS Aurora providing them no company would even bother with PostgreSQL at all. It's 2025 these features are not-negotiable for most use cases.

          b) MongoDB does one thing well. JSON documents. If your domain model is built around that then nothing is faster. Seriously nothing. You can do tuple updates on complex structures at speeds that cripple PostgreSQL in seconds.

          c) Nobody who is architecting systems ever thinks this way. It is never MongoDB or PostgreSQL. They specialise in different things and have different strengths. It is far more common to see both deployed.

          • scosman 5 hours ago

            A) Postgres easily scales to billions of rows without breaking a sweat. After that shard. It’s definitely negotiable.

            • threeseed 5 hours ago

              So does a text file.

              Statements like yours are meaningless when you aren't specific about the operations, schema, access patterns etc.

              If you have a single server, relational use case then PostgreSQL is great. But like all technology it's not great at everything.

              • scosman 5 hours ago

                The use a text file.

                In all seriousness, calling Postgres’ scalability “not-negotiable for most use cases” is wild.

                • threeseed 4 hours ago

                  What's wild is you misrepresenting what I said which was:

                  "built-in, supported, proven scalability and high availability"

                  PostgreSQL does not have any of this. It's only good for a single server instance which isn't really enough in a cloud world where instances are largely ephemeral.

                  • tristan957 3 hours ago

                    Do you mean ephemeral clients or Postgres servers?

                • g8oz 4 hours ago

                  If multiple nodes are needed, then why MongoDB and not a Postgres compatible distributed product like CockroachDB or YugabyteDB?

              • delusional 5 hours ago

                > It's 2025 these features are not-negotiable for most use cases.

                Excuse me? I do enterprise apps, along with most of the developers I know. We run like 100 transactions per second and can easily survive hours of planned downtime.

                It's 2025, computers are really fast. I barely need a database, but ACID makes transaction processing so much easier.

                • redwood 4 hours ago

                  MongoDB has had ACID transactions for many years. I encourage folks to at least read up on the topic they are claiming to have expertise in

                • jeremycarter 5 hours ago

                  Great response. All arguments are valid and fair.

                • riku_iki 6 hours ago

                  Mongo is real distributed and scalable DB, while postgres is single server DB, so main consideration could be if you need to scale beyond single server.

                  • throw14082020 6 hours ago
                    • riku_iki 4 hours ago

                      things still can be true, even if being wrapped into meme videos by haters..

                    • threeseed 5 hours ago

                      High availability is more important than scalability for most.

                      On average an AWS availability zone tends to suffer at least one failure a year. Some are disclosed. Many are not. And so that database you are running on a single instance will die.

                      Question is do you want to do something about it or just suffer the outage.

                      • riku_iki 3 hours ago

                        I think major providers provide PG service with cross zone availability through replication.

                      • codr7 4 hours ago

                        Calling MongoDB a real database compared to PostgreSQL is hilarious.

                        MongDB is basically a pile of JSON in comparison, no matter how much you distribute and scale it.

                        • riku_iki 4 hours ago

                          I think there is no distributed db on the market available with features parity to PgSQL. Distributed systems are hard, and sacrifices need to be made.

                        • jwr 33 minutes ago

                          sigh

                          See https://jepsen.io/analyses for how MongoDB has a tradition of incorrect claims and losing your data.

                          Distributed databases are not easy. Just saying "it is web scale" doesn't make it so.

                          • amazingamazing 5 hours ago

                            It's sad that this was downvoted. It's literally true. MongoDB vs. vanilla Postgres is not in Postgres' favor with respect to horizontal scaling. It's the same situation with Postgres vs. MySQL.

                            That being said there are plenty of ways to shard Postgres that are free, e.g. Citus. It's also questionable whether many need sharding. You can go a long way with simply a replica.

                            Postgres also has plenty of its own strengths. For one, you can get a managed solution without being locked into MongoDB the company.

                            • threeseed 5 hours ago

                              Citus is owned by Microsoft.

                              And history has not been nice to startups like this continuing their products over the long term.

                              It's why unless it is built-in and supported it's not feasible for most to depend on it.

                              • amazingamazing 5 hours ago

                                that's fair, but that's true of mongodb itself too. I wouldn't count that against either of them.

                                • threeseed 4 hours ago

                                  MongoDB makes money selling and supporting MongoDB.

                                  Microsoft does not make money supporting Citus.

                          • 999900000999 6 hours ago

                            Simple.

                            Postgres is hard, you have to learn SQL. SQL is hard and mean.

                            Mongo means we can just dump everyone into a magic box and worry about it later.No tables to create.

                            But their is little time, we need to ship our CRUD APP NOW! No one on the team knows SQL!

                            I'm actually using Postgres via Supabase for my current project, but I would probably never use straight up Postgres.

                            • codr7 4 hours ago

                              If learning SQL is hard, maybe software isn't the best choice of career.

                              Writing code and creating good software requires a lot of mental clarity and effort; that fact is never going to change, not even with AI.

                              • 999900000999 3 hours ago

                                Billions upon billions of value have been created just upon the premise that SQL is hard.

                                Firebase by and almost every NoSql technology is based upon this.

                              • SEJeff 6 hours ago

                                Postgres supports JSONB natively. It literally speaks mongo line protocol and you can shove unstructured json into it.

                                It has supported this since 9.4: https://www.postgresql.org/docs/current/datatype-json.html

                                • 999900000999 5 hours ago

                                  I don't necessarily agree with the above justifications, but in my experience this is basically why teams pick Mongo.

                                  It's easier to get started with.

                                  • SEJeff 4 hours ago

                                    It’s hard to disagree with you on that part. PG is definitely not free to get starts with and requires a bit of setup (hello pg_hba.conf).

                                    • codr7 4 hours ago

                                      Now there's a truth about MongoDB, it's easy to get started with.

                                      But why is that the top priority?

                                      • FridgeSeal 4 hours ago

                                        Because some devs and teams prioritise “get to prod” above literally all else.

                                        Maintainability? Secondary. Security? Secondary. Data-integrity/correctness? Secondary.

                                  • cryptonector 3 hours ago

                                    I thought this was sarcasm till the last sentence. Now I'm not sure.

                                    • chpatrick 6 hours ago

                                      Even as a JSON document store I'd rather use postgres with a jsonb column.

                                      • tiltowait 2 hours ago

                                        Why is that? I found Postgres's JSONB a pill to work with beyond trivial SELECTs, and even those were less ergonomic than Mongo.

                                  • connectsnk 10 hours ago

                                    I understand the criticisms, but in my experience, MongoDB has come a long way. Many of the earlier issues people mention have been addressed. Features like sharding, built-in replication, and flexible schemas have made scaling large datasets much smoother for me. It’s not perfect, but it’s a solid choice.

                                    • beoberha 6 hours ago

                                      I think the amount of people working on large enterprise systems here is a lot smaller than one would think.

                                      Whenever a fly.io post about sqlite ends up in here, there are a scary amount of comments about using sqlite in way more scenarios than it should be.

                                      • dkjaudyeqooe 2 hours ago

                                        "Should be" how?

                                        SQLite is a lean and clean tool, it's very much a candidate for being inserted into all manner of contexts.

                                        What beggars belief is the overly complicated, inefficient, rats nests of trendy software that developers actually string together to get things done, totally unaware of how they are implemented or meant to work.

                                        By comparison using SQLite outside of its "blessed (by who?) use cases" is very practical.

                                        • connectsnk 5 hours ago

                                          True. I have that feeling many times that the enterprise crowd doesnt visits hacker news.

                                          • dkjaudyeqooe 2 hours ago

                                            Why would they be here? They use Oracle.

                                            But mainly because management hasn't worked out how to cancel their licenses without breaking their budgets.

                                          • koakuma-chan 5 hours ago

                                            Why would I use anything other than sqlite?

                                            • margalabargala 4 hours ago

                                              Easy. Sometimes it's more than you need, and there's no reason to use sqlite when you can just write things to a flat text file that you can `grep` against.

                                              • dkjaudyeqooe 2 hours ago

                                                Is this text file static? If not, does all grepping stop when you're updating the file?

                                                • koakuma-chan 2 hours ago

                                                  Damn good point! didn't think about that!

                                            • codr7 4 hours ago

                                              It's still an unstructured blob of JSON, systems built with it are a major pita to maintain.

                                            • kaycebasques 10 hours ago

                                              Bloomberg says it was a $220M cash & stock deal: https://www.bloomberg.com/news/articles/2025-02-24/mongodb-b...

                                              • hartator 10 hours ago

                                                I rather them focus on performance.

                                                Last MongoDB is still slower than MongoDB 3.4. An almost 10-year old release. For both reads and writes.

                                                • memco 10 hours ago

                                                  Can you share more details about the conditions under which it is slow in recent versions? We moved from 3.x to 7 for our main database and after adding a few indexes we were missing we have seen at least an order of magnitude speed up.

                                                • touche_bag 8 hours ago

                                                  I think 8 was a release purely focused on performance, with some big improvements. Comparing 3.4 is kinda unfair.. You were fast with the tradeoff of half your data missing half the time

                                                  • hartator 6 hours ago

                                                    That might explain the write performance degradation, but not the reads.

                                                  • amazingamazing 10 hours ago

                                                    mongodb had consistency issues before v5 if I recall, so take that for what it's worth.

                                                  • infecto 11 hours ago

                                                    Only skimmed through the release..I hope they continue supporting the API but it comes with a little higher confidence that the company behind it is not collecting all your data. Voyage has some interesting embedding models that I have been hesitant to fully utilize due to the lack of confidence in the startup behind it.

                                                  • schnebbau 11 hours ago

                                                    How does MongoDB still have that much available to spend? Everyone I know moved off it years ago.

                                                    • Cshelton 11 hours ago

                                                      We use it a lot for a specific use-case and it works great. Mongo has come a long long way since the release over a decade ago, and if you keep it in Majority Read and Write, it's very reliable.

                                                      Also, on some things, it allows us to pivot much faster. And now with the help of LLMs, writing "Aggregation Pipelines" are very fast.

                                                      • codr7 10 hours ago

                                                        Pretending a pile of json is a database is great for pivoting, not so great for anything else.

                                                        Maintaining apps built on MongoDB is soul killing.

                                                        • rudolph9 2 hours ago

                                                          This

                                                        • burningion 10 hours ago

                                                          I've been using Mongo while developing some analysis / retrieval systems around video, and this is the correct answer. Aggregation pipelines allow me to do really powerful search around amorphous / changing data. Adding a way to automatically update / recalculate embeddings to your database makes even more sense.

                                                          • magarnicle 6 hours ago

                                                            Do you have any tricks for writing and debugging pipelines? I feel like there are so many little hiccups that I spend ages figuring out if that one field name needs a $ or not.

                                                        • isoprophlex 11 hours ago

                                                          Pretty sure they achieved fiscal nirvana by exploiting enterprise brain rot. You hook em, they accumulate tech debt for years, all their devs leave, now they can't move away & you can start increasing prices. Eventually the empty husk will topple over but that's still years away.

                                                          • dimgl 11 hours ago

                                                            Is it possible that they simply have a good product?

                                                            • vosper 11 hours ago

                                                              They do have a good product, but "they accumulate tech debt for years, all their devs leave, now they can't move away" is the story of the place I worked at a few years ago. The database was such a disorganized, inconsistent mess that no-one had the stomach (or budget) to try and get off it.

                                                              • dkjaudyeqooe an hour ago

                                                                This is maybe the biggest reason to have a RDBMS, enforcing discipline to keep your data clean. Ultimately this trumps almost everything else.

                                                                • codr7 4 hours ago

                                                                  Basically every MongoDB I've come across; same story, different faces.

                                                                • isoprophlex 11 hours ago

                                                                  Impossible! It's not based on sqlite, postgres or written in rust, so it must be terrible!

                                                                  • flessner 4 hours ago

                                                                    I never understood this argument, there are many great products running on Java, PHP, Ruby, JavaScript... All of these languages have a "crowd" that hates them for historic and/or esoteric reasons.

                                                                    Great products are in my opinion a function of skill and care. The only benefit a "popular" tool or language gets you is a greater developer pool for hiring.

                                                                  • FridgeSeal 4 hours ago

                                                                    These days almost all the alternatives do 90% of what they cover in a way that’s either using your pre-existing tech stack, or just net-better.

                                                                    There’s probably some extremely specific niche use-cases where it works well, but I suspect they’re pretty few-and-far-between.

                                                                  • xyst 11 hours ago

                                                                    Then they get acquired by BloodMoor and they squeeze every last cent out of the remaining customers.

                                                                    • axpy906 10 hours ago

                                                                      Unironically, this.

                                                                    • bithavoc 11 hours ago

                                                                      that’s what I thought, but every single candidate I interviewed mentioned MongoDB as their recent reference document database, I asked the last candidate if they were self-hosting, the answer is no, they used MongoDB cloud.

                                                                      • tiltowait 2 hours ago

                                                                        Atlas has a generous free tier that is great for hobby projects.

                                                                        • rpep 6 hours ago

                                                                          You cant use the embeddings/vector search stuff this refers to in self hosted anyway, it’s only implemented in their Atlas Cloud product. It makes it a real PITA to test locally. The Atlas Dev local container didn’t work the same when I tried it earlier in the year.

                                                                          • winrid 11 hours ago

                                                                            I self host a handful of mongodb deployments for personal projects and manage self hosted mongo deployments of almost a hundred nodes for some companies. Atlas can get very expensive if you need good IO.

                                                                            • slt2021 11 hours ago

                                                                              if you a developer you wanna use MongoDB as database, not be MongoDB SRE and DBA

                                                                              thats the reason for using Atlas

                                                                              • skatanski 7 hours ago

                                                                                Precisely, and if you are enterprise, you want to have an option to request priority support and have a lot of features out of the box. Also some of the search features are only available in Atlas unfortunately.

                                                                            • paxys 3 hours ago

                                                                              MongoDB is a public company. Its quarterly financial reports will give you a much more accurate picture of the company's health than "everyone you know".

                                                                              • geodel 11 hours ago

                                                                                Everyone you know put a dollar in donation basket while moving off. Mongo collected all and brought Voyage AI

                                                                                • mgfist 11 hours ago

                                                                                  $2.3B in cash as of last quarter

                                                                                  • DarmokJalad1701 11 hours ago

                                                                                    Because they are web-scale obviously.

                                                                                    • yla92 4 hours ago

                                                                                      Mongo Atlas (their cloud offering) is really solid (and expensive)!

                                                                                      • SilasX 11 hours ago

                                                                                        Well, it's referred to as a cash-and-stock deal but I can't find any more detail about how much is stock:

                                                                                        https://seekingalpha.com/news/4412466-mongodb-acquires-voyag...

                                                                                        • porridgeraisin 11 hours ago

                                                                                          There are a lot of people still on it, including the place I worked at last.

                                                                                          It was starting to get expensive though, so we were experimenting with other document stores (dynamodb was being trialled, since we were already AWS for most things, just around the time I left)

                                                                                          • yfontana 10 hours ago

                                                                                            This may be a shock to many HN readers, but MongoDB's revenue has been growing quite fast in the last few years (from 400M in 2020 to 1.7B in 2024). They've been pushing Atlas pretty hard in the Enterprise world. Have no experience with it myself, but I've heard some decently positive things about it (ease of set up and maintenance, reliability).

                                                                                          • markus_zhang 10 hours ago

                                                                                            Looks like everyone is jumping into the AI game. Is there a bubble?

                                                                                            • codr7 4 hours ago

                                                                                              Whatever respect I had left for MongoDB just went out the window, the last thing I want in my database is AI.

                                                                                            • cpursley 11 hours ago

                                                                                              How is MongoDB still a thing when there's already several ways to handle json in Postgres including Microsofts new documentdb extension:

                                                                                              https://gist.github.com/cpursley/c8fb81fe8a7e5df038158bdfe0f...

                                                                                              What am I missing? Are Mongo users simply front end folks who didn't have time to learn basic SQL or back end architecture?

                                                                                              • computerfan494 10 hours ago

                                                                                                I will copy and paste a comment I wrote here previously:

                                                                                                "MongoDB ships with horizontal sharding out-of-the-box, has idiomatic and well-maintained drivers for pretty much every language you could want (no C library re-use), is reasonably vendor-neutral and can be run locally, and the data modeling it encourages is both preferential for some people as well as pushes users to avoid patterns that don't scale very well with other models. Whether these things are important to you is a different question, but there is a lot to like that alternatives may not have answers for. If you currently or plan on spending > 10K per month on your database, I think MongoDB is one of the strongest choices out there."

                                                                                                I have also run Postgres at very large scale. Postgres' JSONB has some serious performance drawbacks that don't matter if you don't plan on spending a lot of money to run your database, but MongoDB does solve those problems. This new documentdb extension from Microsoft may solve some of the pain, but this is some very rough code if you browse around, and Postgres extensions are quite painful to use over the long term.

                                                                                                The reality is that it is not possible to run vanilla Postgres at scale. It's possible to fix its issues with third party solutions or cobbling together your own setup, but it takes a lot of effort and knowledge to ensure you've done things correctly. It's true that many people never reach that scale, but if you do, you're willing to spend a lot of money on something that works well.

                                                                                                • thayne 6 hours ago

                                                                                                  > MongoDB ships with horizontal sharding out-of-the-box

                                                                                                  Maybe it's better than it was, but my experience with Mongodb a decade ago is that that horizontal sharding didn't work very well. We constantly ran into data corruption and performance issues with rebalancing the shards. So much so that we had a company party to celebrate moving off of Mongodb.

                                                                                                  • threeseed 5 hours ago

                                                                                                    > my experience with Mongodb a decade ago

                                                                                                    So before the Apple Watch was released.

                                                                                                    Why is this relevant today ? Technology changes very quickly.

                                                                                                    • cpursley 3 hours ago

                                                                                                      And Apple Watch still sucks as an actual watch vs a Casio.

                                                                                                • amazingamazing 10 hours ago

                                                                                                  MongoDB is not the same as Postgres and jsonb.

                                                                                                  also, I'd challenge your thinking - ultimately the goal is to solve problems. you don't necessarily need SQL, or relations for that matter. that being said, naively modeling your stuff in mongodb (or other things like dynamodb) will cause you severe pain...

                                                                                                  what's also true, which people forget, is naively modeling your stuff with a relational database will also cause you pain. as they sometimes say, normalize until it hurts, and then denormalize to scale and make it work

                                                                                                  the amount of places I've seen that skip the second part and have extremely normalized databases makes me cringe. it's like people think joins are free...

                                                                                                  • pphysch 10 hours ago

                                                                                                    Then your implementation can be as simple as CREATE TABLE documents (content JSONB);. But I suspect a PK and some metadata columns like timestamps will come in handy.

                                                                                                    • amazingamazing 10 hours ago

                                                                                                      sigh - mongoDB is not the same as creating a table with jsonb. for one, you don't have to deal with handling connections. that being said, postgres is great, but it's not the same.

                                                                                                      • pphysch 10 hours ago

                                                                                                        Postgres has ways to simplify connection management, if that is a blocker for you (pooling, pgbouncer, postgrest, etc)

                                                                                                  • ecshafer 10 hours ago

                                                                                                    I have seen a few rather large, production mongodb deployments. I don't understand how so many people chose it as their basis of their applications. There are a not-negligible amount of mongodb deployments I have seen that basically treat mongodb as a memory dump, where they then scan from some key and hope for the best. I have never seen a mongodb solution where I thought that it was better than if they just chose any sql server.

                                                                                                    SQL or rather just some schema based database has a ton of advantages. Besides speed, there is a huge benefit for developers to be able to look at a schema and see how the relationships in the data work. Mongodb usually involves looking at a de facto schema, but with fewer guarantees on types relations or existence, then trawling code for how its used.

                                                                                                    • orochimaaru 10 hours ago

                                                                                                      We use their atlas offering. It’s a bit pricey but we are very happy with it. It’s got a bunch of stuff integrated - vectors, json (obviously), search and charting along with excellent support for drivers and very nice out of the box monitoring.

                                                                                                      Now I could possible spend a bunch of time and do the same thing with open source dbs - but why? I have a small team and stuff to deliver. Atlas allows me to do it fast.

                                                                                                      • skatanski 6 hours ago

                                                                                                        Similar here, there are gotchas though. Some versions ago they've changed their query optimization engine - some of our "slow aggregations" become "unresponsive aggregations" because suboptimal indexes were suddenly used. We had to use hints to force proper indexing. Their columnar db offering is quite bad - I'd say if there's need for analytical functionality, its better to go with a different db. Oplog changes format - and although its expected, it still hurts me every now and then when I need to check something. Similarly at some point they've changed how nested arrays are updated in changestream, which has broken our auditing (its not recommended to use changestream for auditing, we still did ;) ). We've started using NVM instances for some of our more heavily used clusters. Well it turned out recovery of an NVM cluster is much much slower than a standard cluster. But all in all I really like mongodb, if there are no relations - its a good choice. Its also good for prototyping.

                                                                                                        • cpursley 9 hours ago

                                                                                                          There’s a ton of hosted Postgres providers that do all of that and more and are just as simple to use. Neon.tech is really easy to set up and if you need more of a baas (firebase alternative), Supabase. Plus, no vendor lock in. I’ve moved vendors several times, most recently AWS RDS to Neon and it was nearly seamless. Was originally on Heroku Postgres going way back. Try getting off Atlas…

                                                                                                          • orochimaaru 7 hours ago

                                                                                                            Ha - easier said than done in an enterprise, especially when nothing is wrong. Maybe the $$, but at some point the effort involved with supply chain and reengineering dwarfs any “technical” benefit.

                                                                                                            This is why startups like to get into a single supply chain contract with an enterprise - it’s extremely hard to get it setup, but once done very easy to reuse the template.

                                                                                                        • crowcroft 10 hours ago

                                                                                                          If you can learn Mongo you can learn SQL and 'back end architecture' let's be honest the basics are hardly difficult no matter what tool you're using.

                                                                                                          Just because Postgres is good doesn't mean other things can't also be good (and better for some use cases).

                                                                                                          • frankfrank13 11 hours ago

                                                                                                            Enterprise sales

                                                                                                            • nextworddev 10 hours ago

                                                                                                              Mongo is Firestore for entrprise

                                                                                                              • pphysch 10 hours ago

                                                                                                                It's simply not that widespread of knowledge. Modern Postgres users would never suggest Mongo, but a generation of engineers was taught that Mongo is the NoSQL solution, even though it's essentially legacy tech.

                                                                                                                I just ran into a greenfield project where the dev reached for Mongo, and didn't have a good technical reason for it beyond "I'm handing documents". Probably wasn't aware of alternatives. FWIW Postgres would've been a great fit for it, they were modeling research publications.

                                                                                                                • gddgb 10 hours ago

                                                                                                                  Um because it must be worth 2 billion if this acquisition is worth $220 million. I know there’s rules about discussion quality on this site, so I guess we can’t question that.

                                                                                                                • moralestapia 9 hours ago

                                                                                                                  10x exit in a couple years, quite nice on the VC side!

                                                                                                                  On the tech side ... no idea what Mongo's plan is ... their embedding model is not SOTA, does not even outperform the open ones out there, and reranking is a dead end in 2025.

                                                                                                                  I think the value is on Voyage's team, their user base and having a vision that aligned with Mongo's.

                                                                                                                  Congrats!

                                                                                                                  • hweller 8 hours ago

                                                                                                                    >their embedding model is not SOTA, does not even outperform the open ones out there, and reranking is a dead end in 2025.

                                                                                                                    Are you referring to the MTEB leaderboard? It's widely believed many of those test datasets are considered during the training of most open-source text embedding models, hence why you see novel + private benchmarks discussed in many launch blogs that don't exclusively refer to MTEB. There are problems there, and it would be great to see more folks in the search benchmark dataset production space like what Marqo AI has done in recent months.

                                                                                                                    Also what makes you say reranking is dead? Mongo doesn't provide it out of the box but many other search providers like ES, Pinecone, Opensearch do so it must provide some value to their customers? Maybe you're saying it's overrated in terms of how many apps actually need it?

                                                                                                                    disclosure: I work on vector search at Mongo

                                                                                                                    • moralestapia 8 hours ago

                                                                                                                      >Maybe you're saying it's overrated in terms of how many apps actually need it?

                                                                                                                      Yes, my comment leans more towards that, rather than suggesting is useless.

                                                                                                                      • redwood 7 hours ago

                                                                                                                        Taking a step back, accuracy/quality of retrieval is critical as input to anything generated b/c your generated output is only as good as your input. And right now folks are struggling to adopt generative use cases due to risk and fear of how to control outputs. Therefore I think this could be bigger than you think.

                                                                                                                    • touche_bag 8 hours ago

                                                                                                                      Interesting take. Have you benchmarked models on your own data? Cause at this point everything is contaminated so I find it impossible to tell what proper sota is. Also - most folks still just use openai. Last time I checked, reranking always performs better than pure vector search. And to my knowledge it's still the superior fusion method for keyword and vector results.

                                                                                                                      • moralestapia 8 hours ago

                                                                                                                        In my experience, storing RAG chunks with a little bit of context helps a lot when doing the retrieval, then you can skip the whole "rerank" bit and halve your cost and latency.

                                                                                                                        With embedding/generative models becoming better with time, the need for a rerank step will be optimized away.

                                                                                                                    • htrp 10 hours ago

                                                                                                                      Voyage AI basically builds embedding models for vector search

                                                                                                                      • crowcroft 10 hours ago

                                                                                                                        You don't hear the big AI providers talk about embeddings much, but I have to believe in the long run that companies building SOTA foundational LLMs are going to ultimately have the best embedding models.

                                                                                                                        Unless you can get to a point where you can make these models small enough that basically sit in the DB layer of an application...

                                                                                                                        • htrp 9 hours ago

                                                                                                                          That and because the embedding models are much easier to improve with at scale usage (hence why everyone has a deep search/research/RAG tool built into their AI web app now).

                                                                                                                      • Beefin 11 hours ago

                                                                                                                        what's the calculus here? if i'm a developer choosing a low-level primitive such as a database, i'm likely quite opinionated on which models i use.

                                                                                                                        • crowcroft 10 hours ago

                                                                                                                          If I had to guess they might see embedding models become small and optimised enough to the point that they can pull them into the DB layer as a feature instead of being something devs need to actively think about and build into their app.

                                                                                                                          Or it could just be an expansion to their cloud offering. In a lot of cases embedding models just need to be 'good enough' and cheap and/or convenient is a winning GTM approach.

                                                                                                                        • ChrisArchitect 11 hours ago
                                                                                                                        • thecleaner 11 hours ago

                                                                                                                          Curious - do people migrate due to the price tag, ease of use, sth else ?

                                                                                                                          • lpapez 9 hours ago

                                                                                                                            Is Voyage AI web-scale yet?