DeepSeek R1 Unleashed! A New Era of Structured Reasoning with PydanticAI
Join AI Dev Skool & Launch Your AI Startup Today! https://skool.com/ai-software-developers is the community for founders, builders, and AI innovators ready to take their projects to the next level.
If you're launching an AI startup or working on a side project, stop wasting time on endless tutorials and start focusing on what really matters. Inside AI Dev Skool, you'll:
✅ Get expert guidance on the best AI frameworks
✅ Cut through the hype and go straight to what works
✅ Maximize your time with curated resources and real-world insights
✅ Build strong connections with like-minded developers and founders
Our best members actively engage, share, and build—gaining skills while turning ideas into real businesses. If you're serious about AI development and want a shortcut to success, this is the place for you.
🚀 Join now and start building smarter: https://skool.com/ai-software-developers
Discover how DeepSeek R1, a cutting-edge reasoning model from a bold Chinese startup, is challenging AI giants like OpenAI, Anthropic, and Google. In this video, we dive deep into its capabilities and showcase a multi-agent product decision graph built using PydanticAI, DeepSeek R1, and Tavily Search.
🔗 Links & resources:
Skool: https://www.skool.com/ai-software-dev...
Newsletter: https://aidev9.substack.com
Discord server: / discord
PydanticAI: https://ai.pydantic.dev
We are building a Multi-Agent, Multi-Model Decision Graph with PydanticAI, OpenAI GPT-4o and DeepSeek R1. It uses PydanticAI in a multi-agent graph setup, with regular gpt-4o and reasoning models. Despite that R1 cannot use function tools or produce structured output, there are meaningful ways to overcome these shortcomings. The code included in the GitHub repo is for a product buy/skip debate between a Pro and Con agent, moderated by a Moderator agent, all part of a graph with its own state. Most agents use tools such as Tavily Search. Tool use is controlled with the prepare parameter. Finally, when all arguments are finished, all messages are passed to a Reasoning agent with DeepSeek R1, which makes the final Buy or Skip call.
🔥 What You’ll Learn:
1️⃣ How Pro and Con agents debate product buy/skip decisions
2️⃣ Overcoming DeepSeek R1’s limitations with creative workflows
3️⃣ Implementing advanced reasoning models in AI-driven graphs
4️⃣ Using tools like Tavily Search and BeautifulSoup for data-driven decision-making
📦 Key Features:
▶︎ Multi-agent collaboration
▶︎ Structured decision outputs with Pydantic models
▶︎ Seamless reasoning and debate management with PydanticAI graphs
🎓 Who is this for?
Whether you’re an AI developer, data scientist, or enthusiast, this tutorial provides actionable insights into building intelligent, structured agent systems
Masterclass Series:
▶️ Part 1: • PydanticAI: The Best AI Agent Framewo...
▶️ Part 2: • From Chaos to Clarity: LLM Tracing wi...
▶️ Part 3: • 100% Reliable LLM Outputs with Struct...
▶️ Part 4: • Dramatic Improvement! Design Better A...
▶️ Part 5: • Design Better AI Agents With Function...
▶️ Part 6: • Transform You Agents with Result Vali...
▶️ Part 7: • Improve Agent Scalability with Depend...
▶️ Part 8: • Build More Reliable Agents with Retri...
▶️ Part 9: • Better Context Retention with Agent M...
▶️ Part 10: • Building Resilient Agents: Self-Refle...
▶️ Part 11: • Better User Experience with Streaming...
▶️ Part 12: Achieving Precision and Efficiency with Advanced Model Settings
▶️ Part 13: Multi-Model Agents in PydanticAI: Unlocking Next-Gen AI Capabilities
▶️ Part 14: Mastering RAG in PydanticAI: Better AI Agents with Real-Time Data
▶️ Part 15: Masterclass Final Project: AI Resume Writing with Multiple Agents
Timecodes:
00:00 - Welcome to DeepSeek R1
00:16 - Press reactions
01:16 - DeepSeek original paper
02:08 - DeepSeek website
02:36 - Product search - MacBook Pro
03:48 - Product search - NCAA Basketball
05:06 - Career advise
06:18 - Installing DeepSeek R1 on local Ollama
07:44 - Running DeepSeek R1 on Ollama
10:44 - Use case - product debate
11:08 - Community highlight
11:28 - Implementation plan
12:00 - PydanticAI - a quick introduction
13:08 - Graphs in PydanticAI
14:00 - Graph implementation for the product debate
15:16 - DeepSeek R1 limitations
15:48 - DeepSeek workarounds
17:40 - Coding tutorial
37:36 - Summary
#ai #openai #pydantic #ollama #pydanticai #mistral #llm #developer #software #tutorial #genai #llama #local #private #chatgpt #tools #function #calling #deepseek #r1 #graph #tavily #tools
Смотрите видео DeepSeek R1 Unleashed! A New Era of Structured Reasoning with PydanticAI онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь AI Software Developers 28 Январь 2025, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 10,110 раз и оно понравилось 295 людям.