What is EIDORA?
EIDORA is an open-source desktop research software designed for the visual exploration of embedding spaces in cultural datasets. It provides an integrated, project-based local environment that covers the main stages of exploratory embedding space analysis, from importing and linking data sources to computing vector embeddings. The software supports running projection and clustering algorithms and exploring two-dimensional projections through navigation, filtering, and visual encoding. It works with multimodal data and rich contextual metadata commonly found in cultural collections.
How does the process work step by step?
Users can begin with as little as a folder of media files or bring existing embeddings or projection coordinates. They can import multidimensional vectors representing any kind of data or compute embeddings with models for images, video, text, audio, and multimodal combinations. The software allows users to use the workspaces they need as their research develops. Project Bring your collection together Add media sources, connect collection items with metadata, and prepare thumbnails for visual exploration.
Who exactly is EIDORA for?
The software is designed for researchers working with cultural collections who need to import or compute vector embeddings and explore them through interactive projections linked to collection metadata. It is suitable for those who investigate patterns using filters, color mappings, and image previews, and create figures or animations. It supports running projection and clustering algorithms and exploring two-dimensional projections through navigation, filtering, and visual encoding.
How can I get started or download the software?
To get started, users can download the prototype versions for macOS, Windows, or Linux. The macOS version is available as Apple Silicon (M-Series) DMG or Intel (older Macs) DMG, while the Windows version is available as Microsoft Store Windows x64 or Web installer. The Linux version is available as AppImage or DEB package, tested on Ubuntu 24.04. The website provides release notes, checksums, and installation details for each platform.
What specific features does the Discovery view offer?
The software features a Discovery view where users can compute or import two-dimensional projections and explore them through points and media previews. Users can filter and color items by metadata, annotate observations, and save snapshots to revisit or compare views. They can also use the Slicer to explore numerical ranges, such as time periods, while keeping projection coordinates fixed.
How does the Figures feature help with research outputs?
The software includes a Figures feature that allows users to arrange saved views into single- or multi-panel figures with captions, legends, and annotations. Users can export figures and animations, and save compositions to refine them as their analysis develops. This feature helps turn explorations into research outputs.
How does the Embeddings feature work with different representations?
The software includes an Embeddings feature that allows users to import vectors from their own analyses or compute embeddings locally with compatible models from the Model Zoo. Users can compare embedding datasets, cluster items, and carry those groups into visual exploration. This feature works with different representations.
What is the official website of EIDORA?
The official website of EIDORA is eidora.org.
How is EIDORA rated on Trustburn?
On Trustburn, EIDORA has a rating of 4 out of 5 based on 4 reviews.
AI-generated from reviews on this page. Verify anything important with the company directly.