Evolving Responsibilities in AI Data Management
Data Engineering Podcast
00:00
Exploring the Potential of Prompt Compression in AI
This chapter examines the trend of prompt compression in generative AI, focusing on its efficiency in reducing token usage while preserving performance. It also highlights resources like the Linguaa library from Microsoft to support further exploration of this innovative technique.
Transcript
Play full episode
Transcript
Episode notes
Summary
In this episode of the Data Engineering Podcast Bartosz Mikulski talks about preparing data for AI applications. Bartosz shares his journey from data engineering to MLOps and emphasizes the importance of data testing over software development in AI contexts. He discusses the types of data assets required for AI applications, including extensive test datasets, especially in generative AI, and explains the differences in data requirements for various AI application styles. The conversation also explores the skills data engineers need to transition into AI, such as familiarity with vector databases and new data modeling strategies, and highlights the challenges of evolving AI applications, including frequent reprocessing of data when changing chunking strategies or embedding models.
Announcements
Parting Question
The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA
In this episode of the Data Engineering Podcast Bartosz Mikulski talks about preparing data for AI applications. Bartosz shares his journey from data engineering to MLOps and emphasizes the importance of data testing over software development in AI contexts. He discusses the types of data assets required for AI applications, including extensive test datasets, especially in generative AI, and explains the differences in data requirements for various AI application styles. The conversation also explores the skills data engineers need to transition into AI, such as familiarity with vector databases and new data modeling strategies, and highlights the challenges of evolving AI applications, including frequent reprocessing of data when changing chunking strategies or embedding models.
Announcements
- Hello and welcome to the Data Engineering Podcast, the show about modern data management
- Data migrations are brutal. They drag on for months—sometimes years—burning through resources and crushing team morale. Datafold's AI-powered Migration Agent changes all that. Their unique combination of AI code translation and automated data validation has helped companies complete migrations up to 10 times faster than manual approaches. And they're so confident in their solution, they'll actually guarantee your timeline in writing. Ready to turn your year-long migration into weeks? Visit dataengineeringpodcast.com/datafold today for the details.
- Your host is Tobias Macey and today I'm interviewing Bartosz Mikulski about how to prepare data for use in AI applications
- Introduction
- How did you get involved in the area of data management?
- Can you start by outlining some of the main categories of data assets that are needed for AI applications?
- How does the nature of the application change those requirements? (e.g. RAG app vs. agent, etc.)
- How do the different assets map to the stages of the application lifecycle?
- What are some of the common roles and divisions of responsibility that you see in the construction and operation of a "typical" AI application?
- For data engineers who are used to data warehousing/BI, what are the skills that map to AI apps?
- What are some of the data modeling patterns that are needed to support AI apps?
- chunking strategies
- metadata management
- What are the new categories of data that data engineers need to manage in the context of AI applications?
- agent memory generation/evolution
- conversation history management
- data collection for fine tuning
- What are some of the notable evolutions in the space of AI applications and their patterns that have happened in the past ~1-2 years that relate to the responsibilities of data engineers?
- What are some of the skills gaps that teams should be aware of and identify training opportunities for?
- What are the most interesting, innovative, or unexpected ways that you have seen data teams address the needs of AI applications?
- What are the most interesting, unexpected, or challenging lessons that you have learned while working on AI applications and their reliance on data?
- What are some of the emerging trends that you are paying particular attention to?
Parting Question
- From your perspective, what is the biggest gap in the tooling or technology for data management today?
- Thank you for listening! Don't forget to check out our other shows. Podcast.__init__ covers the Python language, its community, and the innovative ways it is being used. The AI Engineering Podcast is your guide to the fast-moving world of building AI systems.
- Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes.
- If you've learned something or tried out a project from the show then tell us about it! Email hosts@dataengineeringpodcast.com with your story.
The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA
The AI-powered Podcast Player
Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
