Fenic: PySpark-Inspired AI DataFrames
For years we’ve survived on ETL → warehouse → BI. When our data was mostly rows and columns, that pipeline just worked. But the minute we pointed LLMs at PDFs, call recordings, and Markdown notes, the wheels came off. Fenic, defined as a cute, PySpark-Inspired DataFrame Framework for AI Workflows, argues we don’t need a brand-new mental model—we need to treat unstructured data like a first-class DataFrame, then borrow decades of lineage, caching, and columnar tricks from analytics engineering.
Fenic compresses three messy stages—OCR/transcription, LLM inference, and context management—into declarative .select() and .withColumn() calls. If it works, analysts could manipulate embeddings, summaries, and toxicity scores the same way they slice numeric columns today.
Questions we’ll raise
Interoperability: Can a Fenic frame flow straight into Polars or DuckDB, or will we be stuck in a bespoke ecosystem?
Scale & cost: Async-batch sounds efficient, but what happens when 10,000 concurrent inferences hit GPU quotas?
Governance: Typedef just open-sourced under Apache-2.0. What’s their roadmap for community governance and long-term maintenance?
We’ll kick things off with a “why now” for DataFrame-native AI. Then, we’ll dive into a live walkthrough of a Fenic pipeline, starting from structured Markdown files. The demo will show how to:
Parse Markdown into row‑wise DataFrames using Fenic helpers
Extract rich metadata and structured sections via Pydantic‑based semantic operations
Analyze error logs inside a DataFrame to surface root causes, fix recommendations, and recurring error patterns
We'll also explore where Fenic fits alongside tools like LangChain, DSPy, and the broader RAG ecosystem.
🤓 Who should attend
Engineer and Data Scientists who love training models
AI Engineers and leaders who have to choose models that balance performance and efficiency
Any machine learning nerds out there interested in the state-of-the-art of post-training pipelines!
Speaker Bios
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021, he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.