weaviate / Verba

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
BSD 3-Clause "New" or "Revised" License
6.38k stars 690 forks source link

Export/backup database #310

Open Wehzie opened 3 weeks ago

Wehzie commented 3 weeks ago

Description

Dear maintainers, if I understand correctly, Verba's local option makes use weaviate embedded. Which as of weaviate's documentation is still in experimental stages. Is it possible to migrate a vector database from weaviate embedded to the dockerized weaviate version?

Additional context

I have installed pip install weaviate-client in order to gain access to an embedded weaviate client, to perform a backup of my data following the basic tutorial.

import weaviate
from weaviate.embedded import EmbeddedOptions
import os

client = weaviate.WeaviateClient(
    embedded_options=EmbeddedOptions(
        additional_env_vars={
            "ENABLE_MODULES": "backup-filesystem",
            "BACKUP_FILESYSTEM_PATH": "/tmp/backups"
        }
    )
    # Add additional options here (see Python client docs for syntax)
)

client.connect()

However I'm not sure where to proceed from there. Thank you for your time.