alright wow building a RAG component is actually a mindblowing experience.

👨‍💻 /uno and /outside, @unofficial

Building something new. 🟪 Host: /venturecapital /adventures /theitinerant

building out the discovery engine @unofficial promised during the demo day!

a search of “NYC marathon runners” should display these very quickly:

1. social content
2. communities
3. media content

not using a GAN! — we use Gemini Pro as the LLM in the flow of data below.

for semantic search we use a different model (i didn’t build that particular embedding flow)

Which GAN foundational model are you using?

Is general search your primary use case or something else you are using rag for?