Here is what you will learn as part of this chapter:
- Improving data integrity with Delta Live Tables (DLT)
- Monitoring data quality with Databricks Lakehouse Monitoring
- Exploring data with Databricks Assistant
- Generating data profiles with AutoML
- Using embeddings for machine-readable data
- Enhancing data retrieval with Databricks Vector Search
- Applying our learning
Here are the technical requirements needed to complete the hands-on examples in this chapter:
- The Databricks Assistant is a newer feature that an administrator can enable. We will show the Assistant in this chapter.
- We use the missingno library to address missing numbers in our project data.
- In the section using AutoML, we reference the AutoML-generated notebook, which you can find in the GitHub repository.
In the chapter
Further Reading