Repository files navigation

Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

Features

• 🏷️Automatic data clustering & labeling:Interactively visualize and navigate overall data structure.

• 🫧Kernel density estimation & density contours:Easily explore and distinguish between dense regions of data and outliers.

• 🧊Order-independent transparency:Ensure clear, accurate rendering of overlapping points.

• 🔍Real-time search & nearest neighbors:Find similar data to a given query or existing data point.

• 🚀WebGPU implementation (with WebGL 2 fallback):Fast, smooth performance (up to few million points) with modern rendering stack.

• 📊Multi-coordinated views for metadata exploration:Interactively link and filter data across metadata columns.

Please visithttps://apple.github.io/embedding-atlas for a demo and documentation.

To use Embedding Atlas with Python:

pip install embedding-atlasembedding-atlas<your-dataset.parquet>

In addition to the command line tool, Embedding Atlas is also available as a Python Notebook (e.g., Jupyter) widget:

fromembedding_atlas.widgetimportEmbeddingAtlasWidget# Show the Embedding Atlas widget for your data frame:EmbeddingAtlasWidget(df)

Finally, components from Embedding Atlas are also available in an npm package:

npm install embedding-atlas

import{EmbeddingAtlas,EmbeddingView,Table}from"embedding-atlas";// or with React:import{EmbeddingAtlas,EmbeddingView,Table}from"embedding-atlas/react";// or Svelte:import{EmbeddingAtlas,EmbeddingView,Table}from"embedding-atlas/svelte";

For more information, please visithttps://apple.github.io/embedding-atlas/overview.html.

For the Embedding Atlas tool:

@misc{ren2025embedding,title={Embedding Atlas: Low-Friction, Interactive Embedding Visualization},author={Donghao Ren and Fred Hohman and Halden Lin and Dominik Moritz},year={2025},eprint={2505.06386},archivePrefix={arXiv},primaryClass={cs.HC},url={https://arxiv.org/abs/2505.06386},}

For the algorithm that automatically produces clusters and labels in the embedding view:

@misc{ren2025scalable,title={A Scalable Approach to Clustering Embedding Projections},author={Donghao Ren and Fred Hohman and Dominik Moritz},year={2025},eprint={2504.07285},archivePrefix={arXiv},primaryClass={cs.HC},url={https://arxiv.org/abs/2504.07285},}

This repo contains multiple sub-packages:

Frontend:

• packages/component: TheEmbeddingView andEmbeddingViewMosaic components.

• packages/table: TheTable component.

• packages/viewer: The frontend application for visualizing embedding and other columns. It also provides theEmbeddingAtlas component that can be embedded in other applications.

• packages/density-clustering: The density clustering algorithm, written in Rust.

• packages/umap-wasm: An implementation of UMAP algorithm in WebAssembly (with theumappp C++ library).

• packages/embedding-atlas: Theembedding-atlas package that get published. It imports all of the above and exposes their API in a single package.

Python:

• packages/backend: A Python package namedembedding-atlas that provides theembedding-atlas command line tool.

Documentation:

• packages/docs: The documentation website.

For more information, please visithttps://apple.github.io/embedding-atlas/develop.html.

This code is released under theMIT license.