---
title: "EmbedAnything"
type: "tool"
slug: "starlightsearch-embedanything"
canonical_url: "https://www.graphcanon.com/tools/starlightsearch-embedanything"
github_url: "https://github.com/StarlightSearch/EmbedAnything"
homepage_url: "https://embed-anything.com/"
stars: 1276
forks: 139
primary_language: "Rust"
license: "Apache-2.0"
categories: ["data-retrieval", "inference-serving"]
tags: ["ai", "high-performance", "large-language-models", "generative-ai", "information-retrieval", "cloud", "indexing", "inference"]
updated_at: "2026-07-07T18:47:21.823685+00:00"
---

# EmbedAnything

> Highly Performant, Modular and Memory Safe Ingestion, Inference and Indexing in Rust 🦀

EmbedAnything is a minimalist yet highly performant embedding pipeline built in Rust. It supports various types of embeddings and seamlessly integrates them into vector databases, offering robust multisource and multimodal support.

## Facts

- Repository: https://github.com/StarlightSearch/EmbedAnything
- Homepage: https://embed-anything.com/
- Stars: 1,276 · Forks: 139 · Open issues: 21 · Watchers: 11
- Primary language: Rust
- License: Apache-2.0
- Last pushed: 2026-06-08T13:30:55+00:00

## Categories

- [Data & Retrieval](/categories/data-retrieval.md)
- [Inference & Serving](/categories/inference-serving.md)

## Tags

ai, high-performance, large language models, generative-ai, information-retrieval, cloud, indexing, inference

## Related tools

- [transformers](/tools/huggingface-transformers.md) - 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models (★ 162,347)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298)
- [firecrawl](/tools/firecrawl-firecrawl.md) - The API to search, scrape, and interact with the web at scale. (★ 147,117)
- [open-webui](/tools/open-webui-open-webui.md) - User-friendly AI Interface (Supports Ollama, OpenAI API, ...) (★ 144,575)
- [vllm](/tools/vllm-project-vllm.md) - A high-throughput and memory-efficient inference and serving engine for LLMs (★ 85,612)
- [PaddleOCR](/tools/paddlepaddle-paddleocr.md) - PaddleOCR: A powerful OCR toolkit for transforming PDFs/images into structured data (★ 84,919)
- [graphify](/tools/graphify-labs-graphify.md) - AI coding assistant skill that transforms various file types into a queryable knowledge graph (★ 79,371)
- [rtk](/tools/rtk-ai-rtk.md) - CLI proxy reducing LLM token consumption by 60-90% (★ 69,253)

## README (excerpt)

```text
<p align ="center">
<img width=400 src = "https://res.cloudinary.com/dltwftrgc/image/upload/v1712504276/Projects/EmbedAnything_500_x_200_px_a4l8xu.png">
</p>



<div align="center">







</div>


<div align="center">

  <p align="center">
    <b> Highly Performant, Modular and Memory Safe</b>
    <br />
    <b> Ingestion, Inference and Indexing in Rust 🦀</b>
    <br />
    <a href="https://embed-anything.com/references/">Python docs »</a>
    <br />
    <a href="https://docs.rs/embed_anything/latest/embed_anything/">Rust docs »</a>
    <br />
    <a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#benchmarks"><strong>Benchmarks</strong></a>
    ·
    <a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#%EF%B8%8Ffaq"><strong>FAQ</strong></a>
    ·
    <a href="https://github.com/StarlightSearch/EmbedAnything/tree/main/examples/adapters"><strong>Adapters</strong></a>
    .
    <a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#-our-past-collaborations"><strong>Collaborations</strong></a>
    .
     <a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#-notebooks"><strong>Notebooks</strong></a>


    
  </p>
</div>


EmbedAnything is a minimalist, yet highly performant, modular, lightning-fast, lightweight, multisource, multimodal, and local embedding pipeline built in Rust. Whether you're working with text, images, audio, PDFs, websites, or other media, EmbedAnything streamlines the process of generating embeddings from various sources and seamlessly streaming (memory-efficient-indexing) them to a vector database. It supports dense, sparse, ONNX, model2vec and late-interaction embeddings, offering flexibility for a wide range of use cases.



<p align ="center">
<img width=400 src = "https://res.cloudinary.com/dogbbs77y/image/upload/v1766251819/streaming_popagm.png">
</p>


<details>
  <summary>Table of Contents</summary>
  <ol>
    <li>
      <a href="#about-the-project">About The Project</a>
      <ul>
        <li><a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#the-benefit-of-rust-for-speed">Built With Rust</a></li>
        <li><a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#why-candle">Why Candle?</a></li>
      </ul>
    </li>
    <li>
      <a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#-getting-started">Getting Started</a>
      <ul>
        <li><a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#-installation">Installation</a></li>
      </ul>
    </li>
    <li><a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#-getting-started">Usage</a></li>
    <li><a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#roadmap">Roadmap</a></li>
    <li><a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#quick-start">Contributing</a></li>
    <li><a href="https://github.com/StarlightSearch/EmbedAnything?tab=readme-ov-file#Supported-Models">How to add custom model and chunk size</a></li>
    
  </ol>
</details>


## 🚀 Key Features


- **No Dependency on Pytorch**: Easy to deploy on cloud, comes with low memory footprint.
- **Highly Modular** : Choose any vectorDB adapter for RAG, with ~~1 line~~ 1 word of code
- **Backend** : Supports Candle, ONNX and cloud models
- **MultiModality** : Works with text sources like PDFs, txt, md, Images JPG and Audio, .WAV
- **GPU support** : Hardware acceleration on GPU as well.
- **Chunking** : In-built chunking methods like semantic, late-chunking
- **Vector Streaming:** : Separate file processing, Indexing and Inferencing on different threads, reduces latency.
- **AWS S3 Bucket:** : Directly import AWS S3 bucket files.
- **Prebult Docker Image** : Just pull it: starlightsearch/embedanything-server
- **SearchAgent** : Example of how you can use index for Searchr1 reasoning.


## 💡What is Vector Streaming

 Embedding mo
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/starlightsearch-embedanything`](/api/graphcanon/tools/starlightsearch-embedanything)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_