This project is a web-based tool that accepts research documents (PDF, DOCX, etc.) and generates a concise, accurate summary of the content. Unlike simple text summarizers, it also understands figures, diagrams, and captions using vision-language models. And aftre extracting the text and the images, it sends the data to an LLM through API and gets the response summary
- Make research easier to understand by providing high-quality summaries.
- Accept multiple file types and work with both text and images.