Weaviate

At a glance

The community member is trying to persist a Weaviate vector store to an S3 bucket, but they are only able to generate the docstore.json, graph_store.json, and index_store.json files, and not the vector_store.json file. They have used this approach with the standard llama_index vector store without any issues. The comments suggest that it may not be possible to save a Weaviate database to S3, and that the Weaviate database is typically saved in the Weaviate database itself, wherever that is hosted. There is no explicitly marked answer in the comments.

PPocketColin

Hello 👋 ! I'm trying to persist a Weaviate vector store to an S3 bucket, but I don't seem to be able to store the actual vector_store.json file. It's generating the docstore.json, graph_store.json, and index_store.json files, but no vector store. Any idea why that's happening? I've used this with the standard llama_index vector store without any issues. The code is pretty simple:

Plain Text

index = VectorStoreIndex.from_documents(documents, storage_context=storage_context, service_context=service_context)
index.storage_context.persist(persist_dir=f"embeddings/{directory}/weaviate/{embedding_model}/{embedding_mode}", fs=self.s3fs)

4 comments

LLogan M

Uhhh it's not possible to save a weavite db to S3? It just gets saved in the weaviate database itself, whereever that is hosted?

PPocketColin

darn....

PPocketColin

I thought that might be true but someone told me they had accomplished it. That's too bad.

PPocketColin

Thanks!

Add a reply

Find answers from the community

Weaviate