{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/c2722b9446aa42f1810fde98bd348942\" frameborder=\"0\" width=\"1662\" height=\"1246\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1246,"width":1662,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1246,"thumbnail_width":1662,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/c2722b9446aa42f1810fde98bd348942-a38a649b889302ff.gif","duration":239.5093,"title":"Enhancing the Sourcing Engine - Doden Bot [Astra]","description":"In this video, I discussed the progress of our sourcing engine and shared a few key points for improvement. First, I need clarity on whether the 10 sources listed for listening styles are all relevant. I also want to enhance our tagging system to include domain, subdomain, and category, allowing for a more interactive experience where users can click on tags to explore related content. Lastly, I questioned whether PDFs need to be stored in Google Drive or if we could pull them from Pinecone for better integration. Please consider these points as we continue to refine the sourcing engine."}