Faiss-rs
This project provides Rust bindings to Faiss, the state-of-the-art vector search and clustering library.
Installing as a dependency
Currently, this crate does not build Faiss automatically for you. The dynamic library needs to be installed manually to your system.
- Follow the instructions here to build Faiss using CMake, enabling the variables
FAISS_ENABLE_C_APIandBUILD_SHARED_LIBS. The crate is currently only compatible with version v1.7.1. Consider building Faiss from this fork,c_api_headbranch, which will contain the latest bindings to the C interface. For example:This will result in the dynamic librarycmake -B . -DFAISS_ENABLE_C_API=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Releasefaiss_c("c_api/libfaiss_c.so" on Linux), which needs to be installed in a place where your system will pick up (in Linux, try somewhere in theLD_LIBRARY_PATHenvironment variable, such as "/usr/lib", or try adding a new path to this variable). For GPU support, don't forget to enable the optionFAISS_ENABLE_GPU. Note:faiss_cmight link dynamically to the nativefaisslibrary, which in that case you will need to install the main shared object (faiss/libfaiss.so) as well. - You are now ready to include this crate as a dependency:
[dependencies]
"faiss" = "0.10.0"
If you have built Faiss with GPU support, you can include the "gpu" feature in the bindings:
[dependencies]
"faiss" = {version = "0.10.0", features = ["gpu"]}
Using
A basic example is seen below. Please check out the documentation for more.
use faiss::{Index, index_factory, MetricType};
let mut index = index_factory(64, "Flat", MetricType::L2)?;
index.add(&my_data)?;
let result = index.search(&my_query, 5)?;
for (i, (l, d)) in result.labels.iter()
.zip(result.distances.iter())
.enumerate()
{
println!("#{}: {} (D={})", i + 1, *l, *d);
}
License and attribution notice
Licensed under either of
- Apache License, Version 2.0, (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0)
- MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT)
at your option.
Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.
This work is not affiliated with Facebook AI Research or the main Faiss software.
8 Sep 22, 2022
2.3k Jan 1, 2023
84 Dec 11, 2022
79 Nov 28, 2022
65 Jan 2, 2023
45 Dec 11, 2022
14 Dec 15, 2022
39 Dec 12, 2022
5 Oct 7, 2022
5 Sep 17, 2022
8 Jul 11, 2021
9 Oct 2, 2023
693 Jan 6, 2023
158 Sep 22, 2022
5.5k Jan 9, 2023
13 Apr 13, 2023
3 Aug 17, 2024
2 Jan 3, 2022
20 Sep 23, 2022