After persisting a Storage Context to my local file system using Python and Llama-Index I can do the following:
index = load_index_from_storage(storage_context)
query_engine = index.as_query_engine()
Yet, I don’t seem to be able to do the equivalent if the storage context is persisted to MongoDB Atlas. I would put this down to a Llama-Index issue except that there is a non working example on the MongoDB Atlas Integrations page.
Solution:
index = VectorStoreIndex.from_vector_store(vector_store)
StorageContext is not required.