How does RAG work, according to Gaurav Sen's AI interview #6?

In the mock interview on Gaurav Sen's channel, candidate Tanishka splits RAG into two stages. An offline ingestion pipeline chunks company documents, converts the chunks into embeddings and stores them in a vector database. Online, the user's question is embedded with the same model, the database returns the most similar chunks, and the LLM answers using those chunks as context alongside the question.

• Tanishka's example query is an employee asking how many leaves they have.
• The search inside the vector database uses approximate nearest neighbour (ANN) algorithms such as HNSW.

Source: our own transcription of the episode. The full conversation is on Gaurav Sen (2026-09-22). Read the whole episode summary →

▸More from this episode