Python + AI: Tool calling
For the final week of our Python + AI series, we're focusing on the technologies needed to build AI agents, starting with the foundation: tool calling (also known as function calling).
We will define our tool call definitions using both JSON schema and Python function definitions, and send those tool definitions to the LLM. We will discover how to properly handle tool call responses from LLMs, enable "parallel" tool calling, and iterate over multiple tool calls.
It is absolutely essential to understand tool calling before diving into agents, so do not miss this foundational session.
If you'd like to follow along with the live examples, make sure you've got a GitHub account.
📌 This session is a part of a series. Learn more here: https://aka.ms/PythonAI/2
Explore the slides and episode resources: https://aka.ms/pythonai/resources
Check out the demos: https://aka.ms/python-openai-demos
Chapters:
00:06 - Welcome and Housekeeping with Anna Heffernan
01:01 - Introduction to Tool Calling with Pamela Fox
03:04 - What is Tool Calling and Why It Matters
07:10 - Step-by-Step: Calling LLMs from Python
10:44 - Defining Function Schemas with JSON
14:00 - Executing Tool Calls in Python
18:44 - Full Tool Calling Flow with LLM Responses
24:03 - Handling Multiple Tools: Parallel vs Looping
35:53 - Tool Calling Support Across Models
41:00 - Error Handling and Model Limitations
47:14 - Improving Reliability with Few-Shot Examples
54:57 - Tool Calling for RAG and SQL Queries
58:26 - What’s Next: Agents, LangChain, and Live Streams
#MicrosoftReactor #learnconnectbuild
[eventID:26298]
Auf dieser Seite können Sie das Online-Video Python + AI: Tool calling mit der Dauer stunde minuten sekunde in guter Qualität ansehen, das der Benutzer Microsoft Reactor 01 Januar 1970 hochgeladen hat, den Link mit Freunden und Bekannten teilen, dieses Video wurde auf Youtube bereits 3,561 Mal angesehen und es wurde von 116 den Zuschauern gefallen. Viel Spaß beim Betrachtenden Zuschauern gefallen!
