Linked Claims Extractor and PDF Parser

This repository contains two independent projects for extracting and processing claims from text, URLs, and PDFs using AI-powered language models (LLMs). Both projects will be published to PyPI, currently the extractor is published.

Projects

1. Linked Claims Extractor: Extracts structured claims from unstructured text, URLs, or PDFs using AI models like Anthropic and OpenAI.
2. PDF Parser: Processes PDF files into structured chunks of text and images, making it easier to analyze and verify claims.

---

Installation

Each project will be installed independently via PyPI:

Linked Claims Extractor

pip install linked-claims-extractor

PDF Parser

PyPI tbd For now install manually by following the intructions in the readme

---

Contributing

Contributions are welcome! Please refer to the individual project READMEs for contribution guidelines.

---

License

This project is licensed under the MIT License. See the LICENSE file for more details.