Pinecone

Hi

I wonder if you have some free time and could enlighten me on the inner workings of GPTPineconeIndex...

1. It is my understanding that every time I call GPTPineconeIndex.from_documents(service_context being gpt-3.5-turbo*), a new vector embedding from gpt-3.5-turbo will be added to the specified Pinecone database. But current OpenAI doesn't support gpt-3.5-turbo embedding in the sense that you can't call their API and pass in a text string then get its embedding back for gpt-3.5-turbo. So how is it possible for Llama-index to do so?
2. When I call GPTPineconeIndex.from_documents, where is the original raw text stored after this? Is it passed to Pinecone as part of the meta data? Or is it stored somewhere locally along with some sort of mapping linking the original raw text to its corresponding vector on Pinecone?
3. Let's say I called GPTPineconeIndex.from_documents on one million documents, but I didn't save all these indices locally and turned off my desktop. Is there a way for me to still do index.query("blablabla") later since technically everything is still on Pinecone?

Any help and guidance would be greatly appreciated 🙂
Thanks in advance.