In this video, I look at a few hacks of how you can get around the fact that the DeepSeek R1 and other reasoning models often don't have structured outputs or function calling.
Colab: https://drp.li/cRLR4
For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: https://www.patreon.com/SamWitteveen
Twitter: https://x.com/Sam_Witteveen
🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes
👨💻Github:
https://github.com/samwit/llm-tutorials
⏱️Time Stamps:
00:00 Intro DeepSeek Paper
00:16 DeepSeek Chat Interface with Search
00:46 DeepSeek Docs
02:05 DeepSeek Chat-Answer
03:16 Demo (Colab): Building Structured Agents with Pydantic AI and DeepSeek
10:02 Extra LLM hack
16:13 Using DeepSeek Reasoner Model as a Tool