What would be a good way to refresh my vector store? So currently my storage_context is set to pinecone. When I updated my documents, I want my vector store to be refresh (essentially delete the original vectors and index the document again). What would be the recommended approach to this?

any recommendation for a good solution to monitor latency during RAG? currently it takes me 10~20 seconds to generate a response, and i want to figure out which stage is causing the latency

Hello I have a newbie question on working with Pinecone:

So I do:

index = GPTVectorStoreIndex.from_documents(
documents, storage_context=storage_context,
service_context=service_context
)

My question is, if my documents get updated and I run the above code again, does my entire index gets replaced by the new document embeddings, or the new embedding simply gets added to the existing index?