Azure API Management with Generative AI - Integrating LLMs and Advanced Features

Explore Azure API Management integration with generative AI models in this comprehensive 39-minute video tutorial. Learn how to incorporate APIM into your AI workflow, understand supported language models, and master authentication processes. Discover key generative AI capabilities in APIM, including token limit management, metric emission, and load balancing between instances. Dive into advanced topics such as prompt logging and semantic caching, with a focus on requirements and practical implementation. Watch a hands-on demonstration, explore potential for chaining operations, and review an excellent example scenario repository. Gain valuable insights into optimizing your AI-powered API management strategy with Azure.

- Introduction
- Adding APIM into the mix
- LLM supported
- Authentication to the LLM
- Adding LLM to APIM
- Azure Portal onboarding experience
- Some key GenAI capabilities in APIM
- Token limits
- Emit token metrics
- Load balancing and switching between instances
- Logging prompts
- Semantic caching
- Requirements
- How it works
- Demo
- Chaining?
- Great example scenario repo
- Summary
- Close