Databricks · Databricks Generative AI Engineer Associate
Source Documents
Databricks Generative AI Engineer Associate · Lesson 3 of 17 · 15:18
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the Databricks Certified Generative AI Engineer Associate exam. In this lesson: choosing authoritative, up-to-date source documents, extracting text with pypdf, unstructured, BeautifulSoup, lxml, and Tesseract, cleaning headers, footers, navigation, and boilerplate, removing duplicates and off-topic or outdated documents, and keeping metadata with every piece of text. Includes three original practice questions.
Preview the topics
- Copperline’s assistant gives two different battery lives for the same headset, because the index holds the manual of the first version and the manual of the current version. What should the team do first?
- Copperline has ten thousand old warranty cards, scanned as images, with printed serial numbers. Which package does the team need to get their text?
- Copperline’s web pages produce chunks full of menu labels and cookie notices, and these chunks keep showing up in the search results. What should the team do?