News for hackers. Stuff that matters.
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by francoismassot on Tuesday January 23, 2024 @08:19AM (#39102938)
Congrats to Qdrant's team, $28M for a Series is really nice.

There are a lot of OSS vector search databases out there, we could probably list the main ones:

- Qdrant: https://github.com/qdrant/qdrant

- Weaviate: https://github.com/weaviate/weaviate

- Milvus: https://github.com/milvus-io/milvus

What else?

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by jillesvangurp on Tuesday January 23, 2024 @10:31AM (#39104705)
There are a few more. Pinecone comes to mind.

And then there are traditional databases and search products that are integrating vector search capabilities as well: Postgres, Elasticsearch, Opensearch, Solr.

They each have their limitations of course but the 28M round suggests a moat that I'm not seeing that clearly in terms of tech. What's so special about qdrant relative to their competition?

At least they are Apache licensed for now. So, that's nice. But that also means e.g. Apache Lucene could borrow some code from them to beef up their vector search capabilities. Which would benefit Elasticsearch, Opensearch, and Solr which all depend on Lucene.

Which raises the question what the point is of QDrant long term and why investors are betting on this as opposed to other things.

It seems to me that the main challenge with vector search is inference cost (at index and query time), not storing the vectors. A secondary concern is the vector comparisons at query time. A good way to cut down on that is to reduce the overall result set using traditional search or query mechanisms. In other words, you need

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by lsaferite on Tuesday January 23, 2024 @10:56AM (#39105045)
Is Pinecone OSS?

I ask because this was the statement from the PP

   There are a lot of OSS vector search databases out there, we could probably list the main ones
   ...
   What else?
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by utopcell on Tuesday January 23, 2024 @01:41PM (#39107661)
Pinecone is not OSS.
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by manishsharan on Tuesday January 23, 2024 @11:39AM (#39105721)
I think there will be enough of market to justify a few more dedicated VectorDB vendors.

From the enterprise perspective, which of these vendors proved the best combination of security, availability, performance and pricing will matter. when we run benchmarks on our (self hosted) LLMs, we do not a clear idea of where we have bottlenecks and we end up assuming its the GPU/memory. And our pilot implementation will never go into production as the security model is nearly non existent in our implementations; the execs AND qa are getting the same RAG outputs. It is all very new to us and our teams. If a vendor can outperform its competition in our tests and show credible security model with segmentation of knowledge, that would be the choice.

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by internet101010 on Tuesday January 23, 2024 @12:24PM (#39106431)
I couldn't agree more. I would add reproducibility to the list of important things, above everything else you mentioned. I looked into Vanna after seeing it on here because generating SQL code by only embedding the schema and business logic seems like a nice, quick middle ground that doesn't require embedding an entire database. However, 88% accuracy in generating the correct query isn't good enough for deployment at the organization-level. "Give me sales for the last quarter as of end of prior month" should return the same result for everyone, without exception.
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by jillesvangurp on Wednesday January 24, 2024 @04:29AM (#39115381)
Depends, short term there is a lot of experimentation and innovation in this space obviously. But long term what matters (for investors) is defensible moats. Most or these products look a bit like one trick ponies to me with some features that are extremely likely to be borrowed by competitors, if they work.

Vector databases are not about hosting LLMs or AI models, they are about storing and comparing embeddings vectors. You generate those with an AI model. OpenAI provides a few of those but GPT 4 is not typically what you'd use for this.

Model training and inference is typically not what a vector database does. You need it but to populate a vector database with content. Qdrant is not an exception to this, it uses third party models and inference technology for this (all the usual suspects basically). I just looked at their documentation to confirm this (but do correct me if I'm wrong).

Additionally, it lists all the classic use cases for vector search as its use cases (image search, semantic search, recommendations, similarity search, etc.). I'm sure it's awesome. But in the end it stores and compares vectors using an open source (and possibly patented?) algorithm. Which means if their approach is particularly good and novel, it will get copied in no time by other open source vector search capable products (i.e. most serious databases and search engines at this point). If it hasn't been already. I don't see dedicated vector database products having any inherent advantage here. Rather the opposite since they lack a lot of features that you might also need.

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by timvisee on Wednesday January 24, 2024 @04:43AM (#39115472)
With regards to competitors picking similar things up, we've this article explaining why a dedicated vector search service is a good idea: https://qdrant.tech/articles/dedicated-service/
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by lmeyerov on Tuesday January 23, 2024 @09:31AM (#39103746)
It's funny taking a numbers view. The most popularly used might not even be these, but vector indexes in existing popular OSS DBs and storage systems people are already using. Afaict earliest would be faiss on disk and vectors in opensearch & elasticsearch, and I'd be curious how say databricks, pgvector and other big ones are getting picked up now that they are out. Most of these supported fast & large-scale indexes even early on (ivfpq, ...) by wrapping faiss and friends. ~All OSS DBs we use now, esp managed, have or are getting vector indexes.

Another one most similar to qdrant we track internally is lancedb. They are clever by supporting an embedded architecture, so an architectural reason to prefer over most existing OSS DBs. In our survey 2 years ago, we predicted specialized vector DBs having regular OSS DBs be the elephant in the room, and missed embedded as a fundamentally different category: https://gradientflow.com/the-vector-database-index/ .

(Good luck to qdrant! I'm happy they waited before raising, hopefully this means they can operate more healthily than otherwise and easier to maintain the discipline to do that!)

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by mritchie712 on Tuesday January 23, 2024 @08:56AM (#39103302)
We use pgvector which if you're already using postgres should be in the running for your use case.

I also like https://github.com/lancedb/lancedb

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by tajd on Tuesday January 23, 2024 @08:57AM (#39103322)
This website for comparing vector database solutions might be handy https://vdbs.superlinked.com/
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by andre-z on Tuesday January 23, 2024 @08:28AM (#39103025)
These are the major ones, correct.
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by epistasis on Tuesday January 23, 2024 @01:16PM (#39107262)
It's fascinating to see the diversity of vector databases! I've chosen to prototype with two, ChromaDB, and LanceDB, based on the ease of using embeddings with them, and had not even heard of these others here. I'm also very excited to go through VectorHub's table of databases:

https://vdbs.superlinked.com

(discovered from sibling comment here: https://news.ycombinator.com/item?id=39103322)

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by daveed on Tuesday January 23, 2024 @01:18PM (#39107297)
I think Activeloop(YC) is too: https://github.com/activeloopai/deeplake/
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by rgbrgb on Tuesday January 23, 2024 @01:40PM (#39107654)
I've been looking at this one to embed in desktop apps https://github.com/unum-cloud/usearch
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by alfalfasprout on Tuesday January 23, 2024 @02:08PM (#39108068)
Sure, but frankly it's historically very hard to build a business around a specialized database, especially if you have competitors that are even 80% as good but free.

The cases where I've seen this work are when the DB offers something way ahead of what their competitors offer. For example, KDB+ was historically unrivaled when it came to ultra high performance time series storage and Aerospike is very hard to beat for extremely high performance multi-node K/V.

Otherwise there's little to stop a larger company from offering the OSS competitor to your DB as a service for a lower cost and invest eng resources to close the gap.

Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by shenli3514 on Tuesday January 23, 2024 @03:08PM (#39109017)
Chroma looks good. https://github.com/chroma-core/chroma 10k+ stars, very easy to use, and can be used as an embedding database
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by morgango on Tuesday January 23, 2024 @04:06PM (#39109830)
Re:Qdrant, the Vector Search Database, raised $28M in a Seri... by bumberg on Tuesday January 23, 2024 @07:23PM (#39111950)
Marqo.ai (https://github.com/marqo-ai/marqo) is doing some interesting stuff and is oss. We handle embedding generation as well as retrieval (full disclosure, I work for Marqo.ai)