PyData    Modern LLM applications rely heavily on embeddings and vector databases for retrieval-augmented generation (RAG). But in 2025, researchers and OWASP flagged vector databases as a new attack surface — from embedding inversion (recovering sensitive training text) to poisoned vectors that hijack...

PyData    LLM apps fail without reliable, reproducible evaluation. This talk maps the open‑source evaluation landscape, compares leading techniques (RAGAS, Evaluation Driven Development) and frameworks (DeepEval, Phoenix, LangFuse, and braintrust), and shows how to combine tests, RAG‑specific...

PyData    Most AI pipelines still treat models like Python UDFs, just another function bolted onto Spark, Pandas, or Ray. But models aren’t functions: they’re expensive, stateful, and difficult to configure. In this talk, we’ll explore why this mental model breaks at scale and share...

PyData    Want to create AI agents that can do more than just generate text? Join us to explore how combining Databricks’ Agent Bricks with the Model Context Protocol (MCP) unlocks powerful tool-calling capabilities. We’ll show you how MCP provides a standardized way for AI agents to interact with external...

PyData    Living on Washington State’s peninsula offers endless beauty, nature, and commuting challenges. In this talk, I’ll share how I built an agentic AI system that creates and compares optimal routes to the mainland, factoring in ferry schedules, costs, driving distances, and live traffic....

PyData    Most ML models excel at prediction, answering questions like Who will buy our product? or Which customers are likely to churn? . But when it comes to making actionable decisions, prediction alone can be misleading. Correlation does not imply causation, and business decisions require understanding...

PyData    PhD students, postdocs and independent researchers often struggle when trying to scale their code and data beyond their local machine, to a HPC cluster or the cloud. This is even more difficult if they don’t happen to have access to IT staff and resources to set up the necessary...

PyData    The world of generative AI is expanding. New models are hitting the market daily. The field has bifurcated between model training and model inference. The need for fast inference has led to numerous Tile languages to be developed. These languages use concepts from linear algebra and borrow common...

PyData    In the world of AI voice agents, especially in sensitive contexts like healthcare, audio clarity is everything. Background noise—a barking dog, a TV, street sounds—degrades transcription accuracy, leading to slower, clunkier, and less reliable AI responses. But how do you solve this in...

PyData    Large language models are often too large to run on personal machines, requiring specialized hardware with massive memory. Quantization provides a way to shrink models, speed them up, and reduce memory usage - all while retaining most of their accuracy. This talk introduces the fundamentals of...