Fastembed-Rs

Visit Tool

fastembed-rs is an Open Source & Models tool that provides a Rust library for generating vector embeddings and reranking. It supports various models for text, sparse text, and image embeddings, along with reranking capabilities.

Claim this tool

2Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is fastembed-rs?

fastembed-rs is a Rust library designed for efficient generation of vector embeddings and reranking, crucial for building advanced AI applications. It offers synchronous usage and leverages @pykeio/ort for high-performance ONNX inference and @huggingface/tokenizers for rapid encodings. The library supports a wide array of pre-trained models for text embeddings (including BGE, MiniLM, MPNet, Nomic, and Qwen3 models), sparse text embeddings (like Splade_PP_en_v1 and BGE-m3), and image embeddings (such as CLIP, ResNet50, and Unicom models). Additionally, it provides reranking functionalities with models like BGE-reranker-base. Developers can easily integrate fastembed-rs into their Rust projects, with options for custom model initialization and support for DirectML on Windows for GPU acceleration.

Best used for

Ideal for developers who need to integrate efficient vector embedding and reranking capabilities into their Rust applications, process various types of data for AI tasks, and leverage pre-trained models for text and image analysis. Especially valuable for building performant search, recommendation, or retrieval-augmented generation systems.

Common actions

generate vector embeddings

rerank search results

process text embeddings

process image embeddings

build AI applications

automated workflowcollaborationopen-sourcelow-code/no-codedeepfakeworkflowsface swapping"AI Agents"github copilot

Capabilities

Key features

Vector embeddings
Reranking
ONNX inference
Fast encodings
Text embedding models
Image embedding models
Sparse text embeddings

Target Audience

developerdata scientist

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What types of embedding models does fastembed-rs support?

fastembed-rs supports a wide range of models for text embeddings (e.g., BGE, MiniLM, Nomic, Qwen3), sparse text embeddings (e.g., Splade_PP_en_v1, BGE-m3), and image embeddings (e.g., CLIP, ResNet50, Unicom). It also includes models for reranking, such as BGE-reranker-base.

Can fastembed-rs be used with custom or local model files?

Yes, fastembed-rs allows for inference using local model files. Developers can utilize the `try_new_from_user_defined(...)` methods of the respective structs to load and use models stored locally, providing flexibility for deployment and custom model integration.

Does fastembed-rs support GPU acceleration on Windows?

Yes, fastembed-rs supports GPU acceleration on Windows through DirectML. By enabling the `directml` feature and passing a DirectML execution provider during model initialization, users can leverage their GPU for faster inference.

Trending

Subcategories trending in Coding & Development

Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce