Spin Up Weaviate

Overview

Spin Up Weaviate is an intermediate, hands-on course for developers and ML engineers who need to get a modern vector database running fast. If you're ready to move from theory to practice, this course provides a direct, step-by-step path to deploying, configuring, populating, and querying Weaviate, one of the most popular open-source vector databases available today. Forget high-level concepts; this course is about execution. You will learn how to use Docker Compose to launch a Weaviate instance locally, define a data schema using its API, and ingest data objects for semantic search. Through a series of practical and guided screencasts and a final, real-world project, you will configure a live database, load it with a dataset of 1,000 articles, and perform your first vector search query using GraphQL APIs to run similarity-based vector search queries. By the end of this 2-hour session, you will have the confidence and skill to deploy and interact with a vector database environment for your own AI applications.

Syllabus

Deploying and Configuring Weaviate

This module focuses on the essential first step: setting up and running your database environment. You will learn how to use Docker Compose to launch a Weaviate instance locally, understand its configuration, and define a data schema that tells the database how to structure incoming information.

Ingesting and Verifying Data

Your database is running; now it's time to use it. This module focuses on the data lifecycle. You will learn how to use Weaviate's REST APIs to ingest data and the GraphQL API to verify retrieval using vector search queries.

Querying Data with Vector Search

With data in your database, this final module teaches you how to get it out intelligently. You will master how to construct and refine vector search queries using GraphQL, understand how query choices affect relevance, and apply these skills to retrieve meaningful results from larger datasets.