From the course: MLOps Essentials: Model Development and Integration
Join today to access over 24,700 courses taught by industry experts.
Integration with generative AI
From the course: MLOps Essentials: Model Development and Integration
Integration with generative AI
- [Narrator] How is model integration done when it comes to generative AI use cases? Generative AI models are huge, and they take significant resources to train, deploy, and serve. Most popular generative AI models, are hence used through a cloud provider service like OpenAI. Even with open-source models, it is preferred to use the deployed versions on popular platforms like AWS and GCP. Hence, the integration work involves testing the generative AI application with the model service, and ensuring that all functionality works as desired. What are some key considerations for integration testing with generative AI? The first key activity is to focus on how the generative AI model is integrated into the application. This indicates resources provisioning, bandwidth provisioning and security. Prompts for GenAI are the integration code between the application and the GenAI models. These need to be used within the application and tested with the model. In cases where the prompts can be…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
