fastembed 5.14.0

Library for generating vector embeddings, reranking locally.
Documentation

Features

Not looking for Rust?

Supported Models

Text Embedding

Quantized versions are also available for several models above (append Q to the model enum variant, e.g., EmbeddingModel::BGESmallENV15Q).

Sparse Text Embedding

Image Embedding

Reranking

✊ Support

To support the library, please donate to our primary upstream dependency, ort - The Rust wrapper for the ONNX runtime.

Installation

Run the following in your project directory:

cargo add fastembed

Or add the following line to your Cargo.toml:

[dependencies]
fastembed = "5"

Usage

Text Embeddings

use fastembed::{TextEmbedding, InitOptions, EmbeddingModel};

// With default options
let mut model = TextEmbedding::try_new(Default::default())?;

// With custom options
let mut model = TextEmbedding::try_new(
    InitOptions::new(EmbeddingModel::AllMiniLML6V2).with_show_download_progress(true),
)?;

let documents = vec![
    "passage: Hello, World!",
    "query: Hello, World!",
    "passage: This is an example passage.",
    // You can leave out the prefix but it's recommended
    "fastembed-rs is licensed under Apache 2.0"
];

 // Generate embeddings with the default batch size, 256
 let embeddings = model.embed(documents, None)?;

 println!("Embeddings length: {}", embeddings.len()); // -> Embeddings length: 4
 println!("Embedding dimension: {}", embeddings[0].len()); // -> Embedding dimension: 384

Qwen3 Embeddings

Qwen3 embedding models are available behind the qwen3 feature flag (candle backend).

[dependencies]
fastembed = { version = "5", features = ["qwen3"] }

use candle_core::{DType, Device};
use fastembed::Qwen3TextEmbedding;

let device = Device::Cpu;
let model = Qwen3TextEmbedding::from_hf(
    "Qwen/Qwen3-Embedding-0.6B",
    &device,
    DType::F32,
    512,
)?;

// Text-only usage with the Qwen3-VL embedding checkpoint is also supported:
// let model = Qwen3TextEmbedding::from_hf("Qwen/Qwen3-VL-Embedding-2B", &device, DType::F32, 512)?;

let embeddings = model.embed(&["query: ...", "passage: ..."])?;
println!("Embeddings length: {}", embeddings.len());

For multimodal text/image usage with Qwen/Qwen3-VL-Embedding-2B:

use candle_core::{DType, Device};
use fastembed::Qwen3VLEmbedding;

let device = Device::Cpu;
let model = Qwen3VLEmbedding::from_hf(
    "Qwen/Qwen3-VL-Embedding-2B",
    &device,
    DType::F32,
    2048,
)?;

let image_embeddings = model.embed_images(&["tests/assets/image_0.png", "tests/assets/image_1.png"])?;
let text_embeddings = model.embed_texts(&["query: blue cat", "query: red cat"])?;

println!("Image embeddings: {}", image_embeddings.len());
println!("Text embeddings: {}", text_embeddings.len());

Nomic Embed Text v2 MoE

The nomic-embed-text-v2-moe model is available behind the nomic-v2-moe feature flag (candle backend). First general-purpose MoE embedding model with 100+ language support.

[dependencies]
fastembed = { version = "5", features = ["nomic-v2-moe"] }

use candle_core::{DType, Device};
use fastembed::NomicV2MoeTextEmbedding;

let device = Device::Cpu;
let model = NomicV2MoeTextEmbedding::from_hf(
    "nomic-ai/nomic-embed-text-v2-moe",
    &device,
    DType::F32,
    512,
)?;

let embeddings = model.embed(&["search_query: ...", "search_document: ..."])?;
println!("Embeddings length: {}", embeddings.len());

Sparse Text Embeddings

use fastembed::{SparseEmbedding, SparseInitOptions, SparseModel, SparseTextEmbedding};

// With default options
let mut model = SparseTextEmbedding::try_new(Default::default())?;

// With custom options
let mut model = SparseTextEmbedding::try_new(
    SparseInitOptions::new(SparseModel::SPLADEPPV1).with_show_download_progress(true),
)?;

let documents = vec![
    "passage: Hello, World!",
    "query: Hello, World!",
    "passage: This is an example passage.",
    "fastembed-rs is licensed under Apache 2.0"
];

// Generate embeddings with the default batch size, 256
let embeddings: Vec<SparseEmbedding> = model.embed(documents, None)?;

BGE-M3 Joint Embeddings

The BGE-M3 model produces dense, sparse, and ColBERT embeddings simultaneously in a single forward pass.

[!WARNING] The default quantized model (BGEM3Q) is optimized for CPUs; passing a GPU execution provider (like CUDA) will fail. For GPU inference or custom requirements, you can export your own custom model (FP32, FP16, or INT8) using the ONNX export script from hf gpahal/bge-m3-onnx-int8 and load it via try_new_from_path.

use fastembed::{Bgem3Embedding, Bgem3InitOptions, Bgem3Model};

// With default options
let mut model = Bgem3Embedding::try_new(Default::default())?;

// With custom options (supporting custom max length up to 8192 tokens)
let mut model = Bgem3Embedding::try_new(
    Bgem3InitOptions::new(Bgem3Model::BGEM3Q)
        .with_max_length(1024)
        .with_show_download_progress(true),
)?;

let documents = vec![
    "Hello, World!",
    "This is an example passage.",
    "fastembed-rs is licensed under Apache 2.0",
    "i dont know"
];

// Generate all three representations in a single forward pass
let output = model.embed(documents, None)?;

println!("Dense dimension: {}", output.dense[0].len()); // -> Dense dimension: 1024

let sparse_emb = &output.sparse[0];
println!("Sparse non-zero tokens: {}", sparse_emb.indices.len());

println!("ColBERT token count: {}", output.colbert[0].len());

Alternatively, local model files can be loaded via try_new_from_user_defined (for inline buffer ONNX models) or try_new_from_path (supporting split external ONNX data files like model.onnx_data):

use fastembed::{Bgem3Embedding, InitOptionsUserDefined, TokenizerFiles, UserDefinedBgem3Model};

let user_model = UserDefinedBgem3Model::new(
    std::fs::read("path/to/model.onnx")?,
    TokenizerFiles {
        tokenizer_file: std::fs::read("path/to/tokenizer.json")?,
        config_file: std::fs::read("path/to/config.json")?,
        special_tokens_map_file: std::fs::read("path/to/special_tokens_map.json")?,
        tokenizer_config_file: std::fs::read("path/to/tokenizer_config.json")?,
    },
);

let mut model = Bgem3Embedding::try_new_from_user_defined(
    user_model,
    InitOptionsUserDefined::default(),
)?;

Image Embeddings

use fastembed::{ImageEmbedding, ImageInitOptions, ImageEmbeddingModel};

// With default options
let mut model = ImageEmbedding::try_new(Default::default())?;

// With custom options
let mut model = ImageEmbedding::try_new(
    ImageInitOptions::new(ImageEmbeddingModel::ClipVitB32).with_show_download_progress(true),
)?;

let images = vec!["assets/image_0.png", "assets/image_1.png"];

// Generate embeddings with the default batch size, 256
let embeddings = model.embed(images, None)?;

println!("Embeddings length: {}", embeddings.len()); // -> Embeddings length: 2
println!("Embedding dimension: {}", embeddings[0].len()); // -> Embedding dimension: 512

Candidates Reranking

use fastembed::{TextRerank, RerankInitOptions, RerankerModel};

// With default options
let mut model = TextRerank::try_new(Default::default())?;

// With custom options
let mut model = TextRerank::try_new(
    RerankInitOptions::new(RerankerModel::BGERerankerBase).with_show_download_progress(true),
)?;

let documents = vec![
    "hi",
    "The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear, is a bear species endemic to China.",
    "panda is animal",
    "i dont know",
    "kind of mammal",
];

// Rerank with the default batch size, 256 and return document contents
let results = model.rerank("what is panda?", documents, true, None)?;
println!("Rerank result: {:?}", results);

Alternatively, local model files can be used for inference via the try_new_from_user_defined(...) methods of respective structs.

DirectML (Windows)

To run models on a GPU via DirectML on Windows, enable the directml feature:

[dependencies]
fastembed = { version = "5", features = ["directml"] }

Then pass a DirectML execution provider when initializing a model:

use fastembed::{TextEmbedding, InitOptions, EmbeddingModel};
use ort::ep::DirectML;

let model = TextEmbedding::try_new(
    InitOptions::new(EmbeddingModel::AllMiniLML6V2)
        .with_execution_providers(vec![DirectML::default().into()]),
)?;

When DirectML is detected, fastembed automatically disables memory pattern optimization and parallel execution on the ONNX Runtime session, as required by the DirectML execution provider.

LICENSE

Apache 2.0