ann-benchmarks VS pgvector

On top of my head, pgvector only supports 2 indexes, those are running in memory only. They don't support GPU indexing, nor Disk based indexing, they also don't have separation of query and insertions.

Also with different people I've talked to, they struggle with scale past 100K-1M vector.

You can also have a look yourself from a performance perspective: https://ann-benchmarks.com/

https://ann-benchmarks.com/ is a good resource covering those libraries and much more.

We utilized the ANN Benchmarks methodology, a standard for benchmarking vector databases. Our tests used the dbpedia dataset of 1,000,000 OpenAI embeddings (1536 dimensions) and inner product distance metric for both Pinecone and pgvector.

Data warehouses are columnar stores. They are very different from row-oriented databases - like Postgres, MySQL. Operations on columns - e.g., aggregations (mean of a column) are very efficient.

Most vector databases use one of a few different vector indexing libraries - FAISS, hnswlib, and scann (google only) are popular. The newer vector dbs, like weaviate, have introduced their own indexes, but i haven't seen any performance difference -

Reference: https://ann-benchmarks.com/

(Blog author here). Thanks for the question. In this case the index for both DiskANN and pgvector HNSW is small enough to fit in memory on the machine (8GB RAM), so there's no need to touch the SSD. We plan to test on a config where the index size is larger than memory (we couldn't this time due to limitations in ANN benchmarks [0], the tool we use).

To your question about RAM usage, we provide a graph of index size. When enabling PQ, our new index is 10x smaller than pgvector HNSW. We don't have numbers for HNSWPQ in FAISS yet.

[0]: https://github.com/erikbern/ann-benchmarks/

In terms of "All You Need" for Vector Search, ANN Benchmarks (https://ann-benchmarks.com/) is a good site to review when deciding what you need. As with anything complex, there often isn't a universal solution.

txtai (https://github.com/neuml/txtai) can build indexes with Faiss, Hnswlib and Annoy. All 3 libraries have been around at least 4 years and are mature. txtai also supports storing metadata in SQLite, DuckDB and the next release will support any JSON-capable database supported by SQLAlchemy (Postgres, MariaDB/MySQL, etc).

pg_vector doesn't perform well compared to other methods, at least according to ANN-Benchmarks (https://ann-benchmarks.com/).

txtai is more than just a vector database. It also has a built-in graph component for topic modeling that utilizes the vector index to autogenerate relationships. It can store metadata in SQLite/DuckDB with support for other databases coming. It has support for running LLM prompts right with the data, similar to a stored procedure, through workflows. And it has built-in support for vectorizing data into vectors.

For vector databases that simply store vectors, I agree that it's nothing more than just a different index type.

The reason https://ann-benchmarks.com is so good, is that we can see a plot of recall vs latency. I can see you have some latency numbers in the leaderboard at the bottom, but it's very difficult to make a decision.

As a practitioner that works with vector databases every day, just latency is meaningless to me, because I need to know if it's fast AND accurate, and what the tradeoff is! You can't have it both ways. So it would be helpful if you showed plots showing this tradeoff, similar to ann-benchmarks.

When talking about Vector Databases, in the market we can find the specialized ones and multi-model, most of the major database providers like Oracle, PostgreSQL or MongoDB, for mention some of them, have integrated a specific solution to retrieve vector data.

For this example, I wanted to focus on how pgvector  – an open-source vector similarity search for Postgres – can be used to identify data similarities that exist in enterprise data.

pgvector supports dense vector search well, but it does not have plan to support sparse vector.

There's an issue in the pgvector repo about someone having several ~10-20million row tables and getting acceptable performance with the right hardware and some performance tuning: https://github.com/pgvector/pgvector/issues/455

I'm in the early stages of evaluating pgvector myself. but having used pinecone I currently am liking pgvector better because of it being open source. The indexing algorithm is clear, one can understand and modify the parameters. Furthermore the database is postgresql, not a proprietary document store. When the other data in the problem is stored relationally, it is very convenient to have the vectors stored like this as well. And postgresql has good observability and metrics. I think when it comes to flexibility for specialized applications, pgvector seems like the clear winner. But I can definitely see pinecone's appeal if vector search is not a core component of the problem/business, as it is very easy to use and scales very easily

The Spring AI project aims to streamline the development of applications that incorporate artificial intelligence functionality without unnecessary complexity. On this example we use features like: Embedding, Prompts, ETL and save all embedding on PGvector(Postgres Vector database)

Official GitHub repository of the pgvector extension

pgvector 0.6.0 was just released and will be available on Supabase projects soon. Again, a special shout out to Andrew Kane and everyone else who worked on parallel index builds.

The pgvector extension adds vector similarity search capabilities to your PostgreSQL database. To use the extension, you have to first create it in your database. You can install the extension, by connecting to your database and running the CREATE EXTENSION command from the psql command prompt:

pgvector has you covered: https://github.com/pgvector/pgvector