Alex Chao on Semantic Kernel, a simple and powerful open source tool for integrating AI into applications.
Subscribe: Apple • Spotify • Overcast • Google • AntennaPod • Podcast Addict • Amazon • RSS.
Alex Chao is a Product Manager at Microsoft focused on Semantic Kernel, an open-source AI and LLM orchestrator. Semantic Kernel (SK) is a lightweight SDK that makes it easy to integrate AI models and plugins into applications. SK has a simple programming model that facilitates the seamless combination of AI models and plugins to craft new user experiences. SK also has connectors that allow easy addition of memories and models, and its ability to integrate plugins extends the capability of apps. SK has been successfully used for tasks such as enabling chats over proprietary data and building AI agents to accomplish specific tasks.
Interview highlights – key sections from the video version:
- Semantic Kernel – Origin Story
- Semantic Kernel (SK): high-level architecture
- Current integrations
- Support for C#, Python, and other languages
- Orchestration for LLMs
- Documentation
- Microsoft’s commitment to SK
- LLM and other models supported
- Who is contributing to SK?
- Popular SK use cases
- How to contribute to SK
- Advice to people who want to transition from data scientist to product manager
Related content:
- A video version of this conversation is available on our YouTube channel.
- Building LLM-powered Apps: What You Need to Know
- Navigating the Future of Search
- Vector Database Primer
- Brian Raymond: ETL for LLMs
- Jerry Liu: An Open Source Data Framework for LLMs
- Andrew Feldman: The Rise of Custom Foundation Models
- Tim Davis: Redefining AI Infrastructure
- Jonas Andrulis: Building and Deploying Foundation Models for Enterprises
- Amin Ahmad: LLMs Are the Key to Unlocking the Next Generation of Search
- Dylan Patel: The Open Source Stack Unleashing a Game-Changing AI Hardware Shift
If you enjoyed this episode, please support our work by encouraging your friends and colleagues to subscribe to our newsletter: