Retrieval adds a "hop" before generation. How would you minimize the time-to-first-token (TTFT) for a user?

When would you choose between Cosine Similarity, Inner Product, and Euclidean Distance (L2) for your vector search?

How would you architect a retrieval system to solve this 'Multi-hop' problem? Example question: How does the Q3 revenue of our Tokyo office compare to the bonus of the CEO?

How do you handle a "Delete" request in your vector database if a user wants their data removed (Right to be Forgotten)?