Seems like Microsoft’s Satya is furious, and who can blame him? They invested so much in OpenAI and then the board does this sneaky change, regardless of the reasons, is shocking they didn’t communicate with Microsoft… If this article is accurate I bet they will have a much harder time securing funding, no one wants to invest in turmoil and uncertainty.
Most often you search the vector db with natural language, there is no special schema to use but you do need to consider how the embedding model is capturing the vectors so it is matched with the embedded query. RAG actually also describes when the LLM is driving the searches, and is the only way I have coded it, the user may ask for something but the LLM creates the search query based on that and the conversation history.
Disappointing