pgvector VS ann-benchmarks

Compare pgvector vs ann-benchmarks and see what are their differences.

pgvector

Open-source vector similarity search for Postgres (by pgvector)

ann-benchmarks

Benchmarks of approximate nearest neighbor libraries in Python (by erikbern)
Our great sponsors
  • InfluxDB - Power Real-Time Data Analytics at Scale
  • WorkOS - The modern identity platform for B2B SaaS
  • SaaSHub - Software Alternatives and Reviews
pgvector ann-benchmarks
77 50
8,586 4,484
9.7% -
9.7 8.1
7 days ago 2 days ago
C Python
GNU General Public License v3.0 or later MIT License
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.

pgvector

Posts with mentions or reviews of pgvector. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2024-03-21.

ann-benchmarks

Posts with mentions or reviews of ann-benchmarks. We have used some of these posts to build our list of alternatives and similar projects. The last one was on 2023-10-30.
  • Approximate Nearest Neighbors Oh Yeah
    5 projects | news.ycombinator.com | 30 Oct 2023
    https://ann-benchmarks.com/ is a good resource covering those libraries and much more.
  • Vector database is not a separate database category
    3 projects | news.ycombinator.com | 2 Oct 2023
    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/

  • How We Made PostgreSQL a Better Vector Database
    2 projects | news.ycombinator.com | 25 Sep 2023
    (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/

  • Do we think about vector dbs wrong?
    7 projects | news.ycombinator.com | 5 Sep 2023
  • Vector Search with OpenAI Embeddings: Lucene Is All You Need
    2 projects | news.ycombinator.com | 3 Sep 2023
    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).

  • Vector databases: analyzing the trade-offs
    5 projects | news.ycombinator.com | 20 Aug 2023
    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.

  • Vector Dataset benchmark with 1536/768 dim data
    3 projects | news.ycombinator.com | 14 Aug 2023
    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.

  • Do we need a specialized vector database?
    2 projects | news.ycombinator.com | 12 Aug 2023
    The article makes the argument that it is easier to query vector spaces when your database already supports them: why use an external vector db when you can use pgvector in postgreSQL ?

    That is a fine argument if you don't mind that pgvector is second-to-worst amongst all open-source vector search implementations, and two orders of magnitude slower than the state of the art [1].

    The author also makes the argument that traditional DBs are better because they are battle-tested, and then goes and rewrites the pgvector plugin from C to rust.

    [1] http://ann-benchmarks.com

  • Unum: Vector Search engine in a single file
    8 projects | news.ycombinator.com | 31 Jul 2023
  • Comparison of Vector Databases
    7 projects | news.ycombinator.com | 31 Jul 2023

What are some alternatives?

When comparing pgvector and ann-benchmarks you can also consider the following projects:

Milvus - A cloud-native vector database, storage for next generation AI applications

faiss - A library for efficient similarity search and clustering of dense vectors.

Weaviate - Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Elasticsearch - Free and Open, Distributed, RESTful Search Engine

qdrant - Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

pinecone - Peer-to-peer overlay routing for the Matrix ecosystem

smlar - PostgreSQL extension for an effective similarity search || mirror of git://sigaev.ru/smlar.git || see https://www.pgcon.org/2012/schedule/track/Hacking/443.en.html

awesome-vector-search - Collections of vector search related libraries, service and research papers

vespa - AI + Data, online. https://vespa.ai

patroni - A template for PostgreSQL High Availability with Etcd, Consul, ZooKeeper, or Kubernetes