rust-sbert - GitLite

KO | EN

gitlite — search

#javascript #python #react #go #rust #macos #java #windows #kubernetes #security #ios #mcp #openai #open-source

rust-sbert

(★ 127)

Rust port of sentence-transformers (https://github.com/UKPLab/sentence-transformers)

File Explorer

Download Latest Version (.zip)

- bench_distilroberta.rs
- bench_sbert.rs
- - convert-tensor.rs
- - dense.rs
  - mod.rs
  - pooling.rs
- - distilroberta.rs
  - mod.rs
  - sbert.rs
- - hf_tokenizers.rs
  - mod.rs
  - rust_tokenizers.rs
  - rust_tokenizers_sentencepiece.rs
- lib.rs
- test_distilroberta.rs
- test_sbert.rs
- Dockerfile
- prepare_distilbert.py
- prepare_distilroberta.py
- prepare_models.py
- requirements.txt
- test_sbert.py
.dockerignore
.gitignore
.travis.yml
Cargo.toml
LICENSE
README.md

# Installation Guide

1. Get the code

git clone https://github.com/cpcdoy/rust-sbert

Downloads the entire project code from GitHub to your computer.

cd rust-sbert

Moves into the project folder you just downloaded.

2. Docker

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Docker Desktop Needed to build and run containers. Install it and keep it running in the background.

docker build -f utils/Dockerfile -t rust-sbert .

Builds a runnable image based on the Dockerfile.

docker run -p 8080:80 rust-sbert

Runs the built image as an actual container.

✅ Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.

3. Python

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r utils/requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.

4. Rust

Medium

Prerequisites

Git Needed to download the project code from GitHub.
Rust (rustup) Installing via rustup also installs cargo.

cargo build --release

Compiles the Rust project.

cargo run

Builds and then immediately runs the program.

✅ If cargo build finishes without errors, it worked. The executable is created under target/.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Rust SBert [![Latest Version]][crates.io] [![Latest Doc]][docs.rs] ![Build Status]

[Latest Version]: https://img.shields.io/crates/v/sbert.svg
[crates.io]: https://crates.io/crates/sbert
[Latest Doc]: https://docs.rs/sbert/badge.svg
[docs.rs]: https://docs.rs/sbert
[Build Status]: https://travis-ci.com/cpcdoy/rust-sbert.svg?branch=master

Rust port of [sentence-transformers][] using [rust-bert][] and [tch-rs][].

Supports both [rust-tokenizers][] and Hugging Face's [tokenizers][].

## Supported models

- **distiluse-base-multilingual-cased**: Supported languages: Arabic, Chinese, Dutch, English, French, German, Italian, Korean, Polish, Portuguese, Russian, Spanish, Turkish. Performance on the extended STS2017: 80.1

- **DistilRoBERTa**-based classifiers

## Usage

### Example

The API is made to be very easy to use and enables you to create quality multilingual sentence embeddings in a straightforward way.

Load SBert model with weights by specifying the directory of the model:

```Rust
let mut home: PathBuf = env::current_dir().unwrap();
home.push("path-to-model");
```

You can use different versions of the models that use different tokenizers:

```Rust
// To use Hugging Face tokenizer
let sbert_model = SBertHF::new(home.to_str().unwrap(), None);

// To use Rust-tokenizers
let sbert_model = SBertRT::new(home.to_str().unwrap(), None);
```

Now, you can encode your sentences:

```Rust
let texts = ["You can encode",
             "As many sentences",
             "As you want",
             "Enjoy ;)"];

let batch_size = 64;

let output = sbert_model.forward(texts.to_vec(), batch_size).unwrap();
```

The parameter `batch_size` can be left to `None` to let the model use its default value.

Then you can use the `output` sentence embedding in any application you want.

### Convert models from Python to Rust

Firstly, get a model provided by UKPLabs (all models are [here][models]):

```Bash
mkdir -p models/distiluse-base-multilingual-cased

wget -P models https://public.ukp.informatik.tu-darmstadt.de/reimers/sentence-transformers/v0.2/distiluse-base-multilingual-cased.zip

unzip models/distiluse-base-multilingual-cased.zip -d models/distiluse-base-multilingual-cased
```

Then, you need to convert the model in a suitable format (requires [pytorch][]):

``` Bash
python utils/prepare_distilbert.py models/distiluse-base-multilingual-cased
```

A dockerized environment is also available for running the conversion script:

```Bash
docker build -t tch-converter -f utils/Dockerfile .

docker run \
  -v $(pwd)/models/distiluse-base-multilingual-cased:/model \
  tch-converter:latest \
  python prepare_distilbert.py /model
```

Finally, set `"output_attentions": true` in `distiluse-base-multilingual-cased/0_distilbert/config.json`.

[sentence-transformers]: https://github.com/UKPLab/sentence-transformers
[rust-bert]: https://github.com/guillaume-be/rust-bert
[tch-rs]: https://github.com/LaurentMazare/tch-rs
[rust-tokenizers]: https://github.com/guillaume-be/rust-tokenizers
[tokenizers]: https://github.com/huggingface/tokenizers/tree/master/tokenizers
[models]: https://public.ukp.informatik.tu-darmstadt.de/reimers/sentence-transformers/v0.2/
[pytorch]: https://pytorch.org/get-started/locally