Skip to main content

Option 2: A local Docker instance

Have you already created a Weaviate instance?

If you have created a cloud instance of Weaviate, you can skip this page and continue with Communicate with Weaviate.

Here, you will create a Weaviate instance using Docker.

Download and run the docker-compose file​

Install Docker on your machine. We recommend following the official Docker installation guide.

Create a new directory and navigate to it in your terminal. Then, create a new file called docker-compose.yml and add the following content:

---
version: '3.4'
services:
  weaviate_anon:
    command:
    - --host
    - 0.0.0.0
    - --port
    - '8080'
    - --scheme
    - http
    image: cr.weaviate.io/semitechnologies/weaviate:1.25.9
    ports:
    - 8080:8080
    - 50051:50051
    restart: on-failure:0
    environment:
      QUERY_DEFAULTS_LIMIT: 25
      AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED: 'true'
      PERSISTENCE_DATA_PATH: '/var/lib/weaviate'
      DEFAULT_VECTORIZER_MODULE: 'none'
      ENABLE_MODULES: 'generative-openai,generative-cohere'
      BACKUP_FILESYSTEM_PATH: '/var/lib/weaviate/backups'
      CLUSTER_HOSTNAME: 'node1'
...

Create a Weaviate instance​

Run the following command to start Weaviate:

docker compose up

Retrieve your Weaviate instance details​

Once the instance is created, you can access it at http://localhost:8080.

Connect to your Weaviate instance​

To connect to the Weaviate instance, use the connect_to_local function.

import weaviate

client = weaviate.connect_to_local()

Provide inference API keys​

Some Weaviate modules can use inference APIs for vectorizing data or large language model integration. You can provide the API keys for these services to Weaviate at instantiation.

This course uses Cohere, so you can provide the Cohere API key to Weaviate through headers={"X-Cohere-Api-Key": <YOUR_KEY>} as shown below:

import weaviate
import os

headers = {
    "X-Cohere-Api-Key": os.getenv("COHERE_APIKEY")
}  # Replace with your Cohere API key

client = weaviate.connect_to_local(headers=headers)

Questions and feedback​

If you have any questions or feedback, let us know in the user forum.