ann-benchmarks
magnitude
Our great sponsors
ann-benchmarks | magnitude | |
---|---|---|
50 | 5 | |
4,568 | 1,610 | |
- | -0.1% | |
8.1 | 0.0 | |
1 day ago | 9 months ago | |
Python | Python | |
MIT License | MIT License |
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.
ann-benchmarks
-
Approximate Nearest Neighbors Oh Yeah
https://ann-benchmarks.com/ is a good resource covering those libraries and much more.
-
Vector database is not a separate database category
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
(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.
- Do we think about vector dbs wrong?
-
Vector Search with OpenAI Embeddings: Lucene Is All You Need
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
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
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?
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.
- Unum: Vector Search engine in a single file
- Comparison of Vector Databases
magnitude
-
Text Classification Library for a Quick Baseline
(3) FastText now supports multiple languages [2].
[1] https://github.com/plasticityai/magnitude#pre-converted-magn...
-
Pgvector – vector similarity search for Postgres
Check out Magnitude, we built it to solve that problem: https://github.com/plasticityai/magnitude
It's still loaded from a file, but heavily uses memory-mapping and caching to be speedy and not overload your RAM immediately. And in production scenarios, multiple worker processes can share that memory due to the memory mapping.
Disclaimer: I'm the author.
Our startup made a package powered by SQLite for this very purpose: https://github.com/plasticityai/magnitude
Might be worth checking out :)
-
Build an Embeddings index from a data source
General language models from pymagnitude
-
Tutorial series on txtai
Backed by the pymagnitude library. Pre-trained word vectors can be installed from the referenced link.
What are some alternatives?
pgvector - Open-source vector similarity search for Postgres
faiss - A library for efficient similarity search and clustering of dense vectors.
Milvus - A cloud-native vector database, storage for next generation AI applications
flashtext - Extract Keywords from sentence or Replace keywords in sentences.
tlsh
vald - Vald. A Highly Scalable Distributed Vector Search Engine
pgANN - Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database.
vald-client-python - A Python gRPC client library for Vald
annoy - Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
finalfusion-rust - finalfusion embeddings in Rust
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows