CODEWITHSUNDEEP
langchainweaviate
figs_and_nuts
figs_and_nuts

Reputation: 5771

Is the creation of local weaviate server from ground up necessary every time I restart the server?

I have a local weaviate server running. I ingest my data in it and can use it for similarity search usecases

The process is

  1. Define an embeddings model using langchain
  2. Ingest the data in the weaviate local client. This includes passing the data through the embedding model
  3. Use it in similarity search

However, whenever I take down the service with docker compose down or restart the VM I have to do all three steps again. Is that entirely necessary? Can I do better? Presently it takes me about 2 hours to get started

Upvotes: 0

Views: 32

Answers (1)

Duda Nogueira
Duda Nogueira

Reputation: 552

Hi! Duda from Weaviate here.

You probably doesn't have the persistence path mapped in your docker-compose.

By default, Weaviate will store data in /var/lib/weaviate

This means that you must map that path to a persistent volume in docker-compose.yaml

something like this:

    volumes:
    - ./weaviate_data/:/var/lib/weaviate

As database, it is expected that after vectorizing and ingesting your data, whenever you restart, your data should still be there.

Check our docker configurator tool for more information: https://weaviate.io/developers/weaviate/installation/docker-compose#configurator

Let me know if this helps :)

Upvotes: 0

Related Questions