

Compound AI Systems with Philip Kiely - Weaviate Podcast #105!
29 snips Oct 17, 2024
Philip Kiely, the leading developer relations at Baseten, shares insights on compound AI systems and their evolution. He discusses breaking tasks into multiple stages for better AI model performance. The conversation covers advancements in multimodal AI and strategies for deploying these systems efficiently. Kiely emphasizes the benefits of smaller models and constrained generation techniques, alongside architectural tips for Kubernetes deployment. Key comparisons are made between various model serving frameworks, focusing on optimizing AI performance while minimizing costs.
Chapters
Transcript
Episode notes
1 2 3 4 5 6 7
Intro
00:00 • 3min
Advancements in Multimodal AI
02:32 • 8min
Exploring Compound AI Systems and Structured Outputs
10:13 • 3min
Unlocking Efficiency with Compound AI Systems
12:43 • 5min
Optimizing AI Deployment on Kubernetes
17:25 • 14min
Exploring Model Serving Frameworks and Simplifying Deployment
31:22 • 2min
Optimizing Compound AI Systems
33:00 • 24min