Hey, AIM community!

Next Wednesday, we begin a new series on Optimization of LLMs! We'll tackle an important topic from first principles: building and optimizing LLMs before they make it to production.

What are the essential concepts and code that underlie the technology, from loss functions and gradient descent to LSTMs, RLHF, and GRPO? Join us to kick off our new series - which we will continue monthly - about Optimization of LLMs.

Last week, we put PydanticAI to the test! 🚀 The team behind Pydantic, the most widely used open-source data validation library, has been making moves raising money and getting pedantic about agents.

"If my team uses Pydantic, should we use PydanticAI for agents?" This question from our community motivated our event. The answer? Well, perhaps yes, kind of! If you're a fan of "that FastAPI feeling," it might be for you, despite its early stage vibes. s/o to the PydanticAI docs too 😆!

🧰 Resources

🧑‍🏫 Concepts: From Data Validation to Agents
🧑‍💻 Code: PydanticAI_A_New_Agent_Framework

🔭 Coming Up!

DeepSeek #OpenSourceWeek

DeepSeek dropped some heavy-hitting repos for their #OpenSourceWeek. Did you catch all of them? We'll cover and discuss FlashMLA, DeepEP, DeepGEMM, Optimized Parallelism Strategies, and 3FS. Perhaps best of all, we'll overview their entire inference system for DeepSeek V3 and R1.

RSVP

RAG: The 2025 Best-Practice Stack

What's the best way to build a RAG application for enterprise? We believe that in 2025, there is a right answer.

Join us to cover the essential production-grade RAG application components and tradeoffs you need to know to create value for yourself and your company in 2025.

RSVP

🌐 Around the Community!

💡 Transformation Spotlight: Arthi Kasturirangan! Learn how this software engineer with 20 years of experience is spearheading her company's innovation, architecture, and solutioning of Gen AI products. Read more about her story!