CatLLM

Python Apps

Classify Survey Responses, Images, and PDF Files: CatLLM is a tool for categorizing, extracting categories, and scoring text and images. Contains custom-functions for scoring the CERAD Constructional Praxis test for dementia classification. [GitHub]

Build Datasets from Web Data: Part of the CatLLM ecosystem, the llm-web-research package enables LLM-powered web research with a focus on accuracy over quantity. Uses a multi-step verification pipeline to catch ambiguous queries before returning potentially incorrect answers. [GitHub]

Classify and Analyze Social Media Posts: CatVader is a fork of CatLLM adapted for social media data. It connects directly to the Threads API to pull your full post history, classify posts into custom categories, and return an enriched dataset with engagement metrics. [Learn more] [GitHub]

Web Apps

Classify Survey Responses: A web-based tool for categorizing survey responses.

Citation

If you use CatLLM in your research, please cite: https://zenodo.org/records/15620202