# Embedding Atlas

> Open-source toolkit from Apple for interactive visualization and exploration of large embeddings in the browser, Python (CLI/Jupyter), and Streamlit.

Embedding Atlas is an MIT-licensed toolkit for working with large text or image embeddings. It provides interactive, in-browser visualizations with cross-filtering and metadata search, and ships as both a Python package (CLI tool, Jupyter widget, Streamlit component) and an npm UI component library. It computes embeddings and 2D projections locally (data stays on-device), and includes WebAssembly implementations of UMAP, approximate nearest-neighbor search, and density-based clustering. Integrations include SentenceTransformers for embedding generation and optional loading of datasets from Hugging Face.

## Features
- Interactive embedding visualization in the browser
- Cross-filtering and metadata search
- Local computation: data does not leave your machine
- Python CLI for quick exploration of large datasets
- Jupyter widget and Streamlit component
- WebAssembly UMAP for dimensionality reduction
- Approximate nearest-neighbor search (HNSW, NN-Descent)
- Density-based clustering and automatic labeling
- Load datasets from local files or Hugging Face
- Export standalone web app from CLI

## Integrations
Jupyter Notebook, Streamlit, SentenceTransformers, Hugging Face Datasets

## Platforms
WEB, DEVELOPER_SDK

## Pricing
Open Source, Free tier available

## Version
0.8.0

## Links
- Website: https://apple.github.io/embedding-atlas/
- Documentation: https://apple.github.io/embedding-atlas/overview.html
- Repository: https://github.com/apple/embedding-atlas
- EveryDev.ai: https://www.everydev.ai/tools/embedding-atlas