@Logan M @jerryjliu0 I am currently using GPTSimpleVectorIndex, but the index file huge and having issues with loading in Google app engine. I am thinking about switching to GPTWeaviateIndex, but not sure if it solve problem.
When I save GPTWeaviateIndex to file to load it back during querying, will data be still stored in the local file, so file size will still be huge?
Is there a way to create index once and query it without saving to local disk?
Using a 3rd party vector store should help somewhat. These databases are optimized for storing and searching vectors.
I don't have experience with every index, but I'm pretty sure the documents/embeddings are not saved to disk (I.e. they are in the vector store)
If you want to connect to a vector store that already has embeddings/documents in it, you can initialize the index with an empty array instead of the actual documents, along with the vector store client
# save index to disk
index.save_to_disk('index_weaviate.json')
# load index from disk
index = GPTWeaviateIndex.load_from_disk('index_weaviate.json', weaviate_client=client)
Is everything store on local disk or no. If not stored in local disk, during query time, will it make a call to Weaviate?
