USearch

Depending on how 'one-off' the query is, sequential read is the right answer. The alternative is indexing the data for ANN, which will generally require doing the equivalent of many queries across the dataset. On the bright side, smart folks have already thought pretty hard about this. In my work, I ended up picking usearch for large-scale vector storage and ANN search. It's plenty fast and is happy working with vectors on disk - solutions which are /purely/ concerned with latency often don't include support for vectors on disk, which forces you into using a hell of a lot of RAM. https://github.com/unum-cloud/USearch

USearch has a sqlite extension that supports various metrics on including Hamming distance on standard sqlite BLOB columns. It gets similar performance and is very convenient. (There's also an indexed variant that does faster lookups, but it uses a special virtual table layout that constrains the types of the other columns in the table.) See https://github.com/unum-cloud/USearch. pip-installable for Python users.

Did someone compared with uSearch (https://github.com/unum-cloud/USearch)?

Embedded usearch vector database. https://github.com/unum-cloud/USearch

Okay, bummer. No support for quantized datatypes yet and from the docs I cannot see anything that mentions fast brute force search. I personally don't need an index. But I see that https://github.com/unum-cloud/usearch which is used by duckdb-vss in turn uses https://github.com/ashvardanian/simsimd which should make a really fast exact vector similarity search possible. Am I missing something here?

USearch is this type of library: https://github.com/unum-cloud/usearch Used in ClickHouse and a few other DBMS.

In case you are searching for fun use-cases, here's how one experiment with weird similarity metrics & kNN data-structures via Cppyy (for C++ kernel), Numba (for Python), or PeachPy (for x86 Asm), interacting with a precompiled engine: https://github.com/unum-cloud/usearch/blob/main/python/READM...

This is great, I'll be returning to this tool often. Thanks. A few suggestions and ideas for futher projects. -allow for "keyword", -negate operators and "mult word string" searches, [Pubmed](https://pubmed.ncbi.nlm.nih.gov/advanced) is what I'd consider an Ideal search interface -allow for regex, or direct sql lookups with limited query time ratelimited by POW. for example, if the server is under load, require a token from something like [anubis](https://anubis.techaro.lol/) and lower the maximum DB query time -Index the title of all discussion/forum type posts with a VectorDB for semantic search. And add an option to sort by replies. (Like [answer overflow](https://github.com/AnswerOverflow/AnswerOverflow))This would make it possible to find relevant discussions among ~60B messages. ScyllaDB doesn't support vector search, so I'd sugges

I wish I'd had a short answer :) For years, I've had a hope to build it in the form of an open-core project: open-source SotA solutions for Storage, Compute, and AI Modeling built bottom up. You can imagine the financial & time burden of building something like that with all the weird optimizations and coding practices listed above. A few years in, with millions spent out of my pocket, without any venture support or revenue, I've decided to change gears and focus on a few niche workloads until some of the Unum tools become industry standards for something. USearch was precisely that, a toy Vector Search engine that would still, hopefully, be 10x better than alternatives, in one way or another: <https://www.unum.cloud/blog/2023-11-07-scaling-vector-search...>. Now, ScyllaDB (through Rust SDK) and YugaByte (through C++ SDK) are the most rec

I use usearch for the engine https://github.com/unum-cloud/usearch/. It's fast. The vectors are stored in DB and added to usearch at startup for retreival. There is also FAISS.

Check out Unum’s usearch. It beats anything, and is super easy to use. It just does exactly what you need. https://github.com/unum-cloud/usearch

Just tried usearch against ol’ faithful np.dot, and found the latter to be 8x faster than usearch on 10m brute force scan as described in their readme [1] for top 50 matches. Identical output result. 1.74 seconds for numpy and around 12 seconds for usearch on an M2 max with enough ram to hold the vectors without swapping. [1] https://github.com/unum-cloud/usearch?tab=readme-ov-file#exa...

Swap out FAISS with usearch, you get all the awesome SIMD acceleration (via dynamic dispatch), optional compression. Not affiliated but really cool tech. https://github.com/unum-cloud/usearch

Try Usearch - it's really fast and under rated https://github.com/unum-cloud/usearch