Latent Scope
Latent Scope reveals the hidden structure in unstructured data through intuitive visual maps, transforming data exploration from a tedious analysis into an immediate and comprehensive view.
Overview
- Contributor
- Ian Johnson
- Github
- Code
- Stars
- 686
- Forks
- 27
More Information
Latent Scope is an open-source tool that leverages the latest in LLMs to embed, visualize, cluster, and categorize your data.
It includes a pipeline tool to systematically process your datasets and an exploration interface to visualize and edit your categorized data. Latent Scope can be run fully locally using only open-source models or leverage several popular model providers.
The following examples demonstrate the kinds of perspective and insights you can gain from your unstructured text data.
- Explore free-responses from surveys in this datavis survey analysis
- Cluster thousands of GitHub issues and PRs
- Analyze the popularity and content of 10,000 tweets
- Sort through two hundred years and 50,000 US Federal laws
Contribute
Join the DiscordContributors
About Ian
Ian is the founder of Latent Scope. He was previously a Staff Software Engineer at Stability AI, Senior Data Visualization Developer at Observable, and a User Experience Engineer at Google. He was also a Teaching Assistant at Florida State University.
More from Ian
-
Latent Scope
Uncovering the Hidden Patterns in Your Data
Other Projects
-
An open benchmark which helps you understand how well your computer can handle local AI task
-
Web Applets is an open specification for building software that both humans and AI can understand and use together.
- Contributor
- Rupert Manfredi
-
Transformer Lab is an open source platform that allows anyone to build, tune, & run Large Language Models locally, without writing code.
- Contributors
- Ali Asaria, Tony Salomone