{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/53e68b0eb5ab49948111a3fcf6286b7f\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/53e68b0eb5ab49948111a3fcf6286b7f-00001.gif","duration":257.1543359820001,"title":"Sycamore: Semantic Data Preparation using LLMs","description":"We demonstrate Sycamore, a semantic data preparation system for search. Sycamore is a Python-native system for preparing unstructured data using LLMs. In this demo, we show how to segment a PDF, extract entities like titles and authors, and create vector embeddings with only a few lines of code."}