Nina Lopatina
Nina is a Staff Developer Relations Engineer at Unstructured.io, specializing in AI-driven data processing. Previously, she was Head of Innovation at Nurdle AI and Director of Data Science at Spectrum Labs, where she led model iteration and data quality efforts until its acquisition by ActiveFence. She also held leadership roles at In-Q-Tel, driving AI and data science initiatives. With a PhD in Neuroscience from the University of Maryland Baltimore, Nina brings deep expertise in AI, data science, and innovation.
Speaker Sessions
Achieving Seamless Ai-augmented Software Development with Automated Etl+ for Genai
This workshop will demonstrate how to leverage Unstructured.io's fully automated ETL+ solution to streamline data processing for AI-driven software development. We start with ETL for GenAI: continuously harvesting newly generated unstructured data from systems of record, transforming it into LLM-ready formats using our optimized, pre-built pipelines, and writing it to downstream locations such as vector or graph databases. Then we add the +: all the features enterprise users need to eliminate ETL headaches and stay focused on applications that drive their business forward. Participants will gain practical insights into using the brand new Playground feature in the Unstructured API: transforming a local unstructured file into partitioned, chunked, enriched, and embedded json, while being able to visualize and understand each step in the pipeline. Participants will also learn about all of Unstructured's offerings: seamlessly integrated third-party services, incremental vector syncing, contextual chunking, ane more. We will also review how to fully customize your ETL pipelines and deploy them within existing infrastructure environments, either with a no code UI or via API. Attendees will leave with actionable strategies to address the complex challenges of handling diverse data types and sources in AI applications.