Python + AI: Level Up

5:00 PM - 6:00 PM (UTC)

Our third stream in the Python + AI series is all about vision models! Vision models are LLMs that can accept both text and images, like GPT 4o and 4o-mini. You can use those models for image captioning, data extraction, question-answering, classification, and more! We'll use Python to send images to vision models, build a basic chat-on-images app, and build a multimodal search engine.

5:00 PM - 6:00 PM (UTC)

In our fifth stream of the Python + AI series, we'll discover how to get LLMs to output structured responses that adhere to a schema. In Python, all we need to do is define a @dataclass or a Pydantic BaseModel, and we get validated output that meets our needs perfectly. We'll focus on the structured outputs mode available in OpenAI models, but you can use similar techniques with other model providers. Our examples will demonstrate the many ways you can use structured responses, like entity extraction, classification, and agentic workflows.

5:00 PM - 6:00 PM (UTC)

Now that we're more than halfway through our Python + AI series, we're covering a crucial topic: how to use AI safely, and how to evaluate the quality of AI outputs. There are multiple mitigation layers when working with LLMs: the model itself, a safety system on top, the prompting and context, and the application user experience. Our focus will be on Azure tools that make it easier to put safe AI systems into production. We'll show how to configure the Azure AI Content Safety system when working with Azure AI models, and how to handle those errors in Python code. Then we'll use the Azure AI Evaluation SDK to evaluate the safety and quality of the output from our LLM.

5:00 PM - 6:00 PM (UTC)

Now that we're more than halfway through our Python + AI series, we're covering a crucial topic: how to use AI safely, and how to evaluate the quality of AI outputs. There are multiple mitigation layers when working with LLMs: the model itself, a safety system on top, the prompting and context, and the application user experience. Our focus will be on Azure tools that make it easier to put safe AI systems into production. We'll show how to configure the Azure AI Content Safety system when working with Azure AI models, and how to handle those errors in Python code. Then we'll use the Azure AI Evaluation SDK to evaluate the safety and quality of the output from our LLM.

5:00 PM - 6:00 PM (UTC)

For the penultimate session of our Python + AI series, we're building AI agents! We'll use many of the most popular Python AI agent frameworks: Langgraph, Semantic Kernel, Autogen, Pydantic AI, and more. Our agents will start simple and then ramp up in complexity, demonstrating different architectures like hand-offs, round-robin, supervisor, graphs, and ReAct.

5:00 PM - 6:00 PM (UTC)

In the final session of our Python + AI series, we're diving into the hottest technology of 2025: MCP, Model Context Protocol. This open protocol makes it easy to extend AI agents and chatbots with custom functionality, to make them more powerful and flexible. We'll show how to use the official Python FastMCP SDK to build an MCP server running locally and consume that server from chatbots like GitHub Copilot. Then we'll build our own MCP client to consume the server. Finally, we'll discover how easy it is to point popular AI agent frameworks like Langgraph, Pydantic AI, and Semantic Kernel at MCP servers. With great power comes great responsibility, so we will briefly discuss the many security risks that come with MCP, both as a user and developer.