DeepLearning.AI has expanded its course catalog with new offerings that cover practical areas such as agentic AI, function-calling and data extraction, and carbon-aware computing practices.
Explore our new courses for free:
AI Agents in LangGraph
LangChain, a popular open source framework for building LLM applications, recently introduced LangGraph. This extension allows developers to create highly controllable agents.
In AI Agents in LangGraph you will learn to build an agent from scratch using Python and an LLM, and then rebuild it using LangGraph to learn its components and how to combine them to build flow-based applications.
Additionally, you will learn about agentic search, which returns multiple answers in an agent-friendly format, enhancing the agent’s built-in knowledge. This course will show you how to use agentic search in your applications to provide better data for agents to enhance their output.
In this course you will develop an AI agent that interacts with databases using natural language, simplifying the process for querying and extracting insights.
Building Your Own Database Agent, created in partnership with Microsoft and taught by Adrian Gonzalez Sanchez, Data and AI Specialist at Microsoft, is designed for developers, data professionals, as well as business analysts and professionals who want more sophisticated interaction with their databases through natural language instead of complex SQL queries.
This course will teach you two critical skills for building applications with LLMs: function-calling and structured data extraction.
Function-calling allows you to extend LLMs with custom capabilities by enabling them to form calls to external functions based on natural language instructions. Structured data extraction enables LLMs to pull usable information from unstructured text.
In Function-Calling and Data Extraction with LLMs you’ll work with NexusRavenV2-13B, an open source model fine-tuned for function-calling and data extraction. The model, freely available on Hugging Face, outperforms GPT-4 in some function-calling tasks, and has 13 billion parameters so it can be hosted locally.
This short course was made in collaboration with Google Cloud and taught by Nikita Namjoshi, Developer Advocate at Google Cloud and Google Fellow on the Permafrost Discovery Gateway.
Training, fine-tuning, and serving generative AI models can be demanding in terms of compute and energy. But these processes don't have to be as carbon-intensive if you choose when and where to run them in the cloud.
%20(1200%20%C3%97%20200%20px)%20(1).png?upscale=true&width=602&upscale=true&name=Email%20Header%20Options%20(1200%20%C3%97%20300%20px)%20(1200%20%C3%97%20200%20px)%20(1).png)
.png?upscale=true&height=50&upscale=true&name=White%20Circle%20Profile%20Photo%20Instagram%20Post%20(3).png){kind=small}