Texture is a system for exploring and creating structured insights with your text datasets.
- Interactive Attribute Profiles: Texture visualizes structured attributes alongside your text data in interactive, cross-filterable charts.
- Flexible attribute definitions: Attribute charts can come from different tables and any level of a document such as words, sentences, or documents.
- Embedding based operations: Texture helps you use vector embeddings to search for similar text and summarize your data.
Install texture with pip:
pip install texture-viz
Then you can run in a python script or notebook by providing a dataframe with your text data and attributes.
import texture
texture.run(df)
Texture allows you to customize attribute visualizations based on a schema and configure different tables to tailor how the interface presents your data. For more details and examples, check out our documentation.
See DEV.md for dev workflows and setup.