That is incorrect. Vector lookup like qdrant is just one technique that classifies as RAG. RAG is any technique that feeds external information to an LLM's context window. The technique can be keyword...
I feel like you're not understanding what I'm asking. I'm trying to figure out where you're sourcing the data on the backend from and if it's possible to interface with that more directly.
For example, I brought up fundamentals pod, are you transcribing yourself? What if I wanted to limit my search to one of his 12/other podcasts? I I wanted to add a podcast, do I just add it to your index somehow or do I need to enable transcription in some way etc.
For example, I brought up fundamentals pod, are you transcribing yourself? What if I wanted to limit my search to one of his 12/other podcasts? I I wanted to add a podcast, do I just add it to your index somehow or do I need to enable transcription in some way etc.
2