Hacker News Reader

Comment by fdgsdfogijq | Hacker News Reader

Which open source libraries is pinecone wrapping?

I’m not sure where the other commenter gets their confidence, but Pinecone is not wrapping any open source vector-search library. We offer three index types (in-memory, in-memory graph-based, hybrid memory + disk), and all are proprietary.

We do have articles about Faiss and HNSW and all sorts of other vector-search and NLP topics, so it’s possible that’s where the confusion comes from.

so, how does your proprietary solution compare against FAISS, eg with 10M dense vectors of 1024 dimensions?

They used to publish some benchmarks on their site, but seem to have removed them. You can find them on archive.org[1]. I guess it is understandable, since vector search performance is pretty unpredictable, and depends on a lot of factors. If their target market is people who want vector search without needing to read a bunch of papers first, benchmarks might be more confusing than they are helpful.

edit: While I do think it's understandable, it's not great for transparency. Even if they don't want to open-source their index, I would admire it if they were willing to give ann-benchmarks[2] an API key to publish some independent results.

Disclaimer: I work on vector search at a different company

[1] https://web.archive.org/web/20210227105542/https://www.pinec... [2] https://github.com/erikbern/ann-benchmarks

FAISS

This is incorrect.

Strange comments and denial coming from the person who submitted a post about pinecone wrapping Faiss a year ago https://news.ycombinator.com/item?id=27502458

Yeah, what's this landing page about? https://www.pinecone.io/managed-faiss/

That's a very old and experimental page -- hence the "early access" mentions. Glad you pointed it out so we can delete it.

If you really think that's enough to build a real product, go for it. Even open-source companies (Elastic, Mongo, Scylla) have to build tons of infra around their core codebase in order to make it an actual cloud product.

Not that easy, the founder was a director at AWS. This is just devops/obfuscation on top of an open source library:

FAISS

Pinecone doesn’t use Faiss, nor ScaNN. We love Faiss and even teach people to use it[1]. There happens to be a sizable population of engineers who need more than what Faiss provides (like live index updates and metadata filtering, for example), and can’t be bothered or aren’t being paid to customize and manage open-source libraries all day.

[1] https://www.pinecone.io/learn/faiss/

So you guys developed and implemented state of the art neural network vector search from scratch? in a year? and something better than libraries with tens of contributors over years of research?

Most vector search research teams are a lot smaller than you suggest, and haven't been around that long (e.g. the FAISS paper was published in 2017).

From public info, you can see they have at least one researcher working there. It's believable to me that they could have some new innovations, especially since the product space they're focusing on is different from other teams working on vector search. State-of-the-art for a specific set of constraints is still state-of-the-art.

However, considering how much of their edu-marketing content is posted to HN, it would be great if they could share more details about the internals of their index with the community. One of the great things about vector search is how many techniques are open sourced or documented in papers :).

Disclaimer: I work on vector search at a different company

Many very competitive vector search libraries are done by small teams.

HNSW in NMSLIB[1] is mostly 3 people's work and it's very competitive[2].

[1] https://github.com/nmslib/nmslib

[2] http://ann-benchmarks.com/glove-100-angular_10_angular.html

I actually built a similar solution supporting similar operations (including filtering by meta-data) using open-source libraries. Took me about 2 weeks net.

I can see a clientele for such database (people who want a turnkey solution), but honestly it looks like an attempt to use a dev-ops solution to address deeper issues with problem formulation: e.g.

1. Is there really a need to search all items in the database? can subsampling make simple similarity comparison feasible?

2. Do the embeddings really need to have that many dimensions? Can we reduce their dimensionality and fit them in RAM?

3. Is embedding accurate enough compared to pairwise comparison? Can we formulate the problem to make the latter feasible?

I also could not find any explanation of the underlying algorithms, especially around meta-data filtering, which is not solved by FAISS as well as their accuracy. (happy to hear otherwise)

Reply on news.ycombinator.com