{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/73ba4d3e56324cc698a91f7c3c2affcc\" frameborder=\"0\" width=\"1660\" height=\"1245\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1245,"width":1660,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1245,"thumbnail_width":1660,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/73ba4d3e56324cc698a91f7c3c2affcc-d1298b96681155fe.gif","duration":118.699,"title":"Building a Video Intelligence Pipeline with AI Tools 🚀","description":"Hey, I'm Anish from Austin, and I wanted to share my video intelligence pipeline that I built using Next.js and FastAPI. It allows users to input TikTok or YouTube short links, and it processes the videos to extract views and transcriptions using YTDLP and Whisper. I also implemented a vector database to search for specific content, like videos of a blue Razer, which you can see in action. I think this approach could be really effective for handling large datasets, similar to what ShofoAI is doing. I'd love to hear your thoughts on this idea!"}