Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
This tutorial demonstrates how to enhance Large Language Models (LLMs) with four key capabilities to build more effective AI applications. Learn to implement memory systems for maintaining context across conversations, structured outputs using Pydantic for reliable data handling, tool integration through function calling to perform real-world actions, and retrieval techniques to access external knowledge. The entire implementation uses Python and Ollama for local development, making it accessible for AI engineers. The content follows Anthropic's research on building effective agents and includes comprehensive code examples. Perfect for developers looking to create AI applications that solve practical problems by augmenting LLMs with these essential capabilities.
Syllabus
00:00 - Welcome
00:39 - The super augmented LLM
02:07 - Full-text tutorial and source code on MLExpert.io
02:44 - Memory
05:32 - Structured output
10:46 - Tools function calling
22:38 - Retrieval
28:43 - Conclusion
Taught by
Venelin Valkov