{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/d8151a5d2da34218b86a6766ff04893e\" frameborder=\"0\" width=\"1152\" height=\"864\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":864,"width":1152,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":864,"thumbnail_width":1152,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/d8151a5d2da34218b86a6766ff04893e-77e38432427a03aa.gif","duration":179.634,"title":"Demo of OpenLX Paper Summarizer App","description":"This Loom demonstrates the local setup and key features of a paper browsing and summarization web app. It runs via docker-compose up, bringing up the frontend on localhost 3000 and backend on localhost 8000 while the database becomes healthy. The interface lets users filter papers by topics such as Machine Learning and Robotics and by year, and it fetches 37 papers from the OpenLX API key; users can click a DOI for the paper URL and generate plain text summaries. The author also discusses design decisions for the summarize endpoint and notes a fix for authors being listed twice when ingesting live data due to different affiliations."}