Built with Bauplan

Analyze PDFs using Bauplan for data preparation and OpenAI’s GPT for text analysis.

Orchestrated Write-Audit-Publish pattern for ingesting parquet files to Iceberg tables.

Build near real-time analytics pipeline with WAP pattern and visualize metrics with Streamlit.

Convert PDFs into structured, analyzable tables using LLMs.

End-to-end ML pipeline for predicting taxi trip tips with Streamlit data viz.

Embedding-based recommender system for music playlists.

End-to-end entity matching for e-commerce, using OpenAI’s off-the-shelf LLM APIs for accurate matching.

End-to-end data engineering repo using Mage & the medallion architecture.

Build a RAG system with Pinecone and OpenAI over StackOverflow data.

Serverless data product with built-in quality checks using Lambda and Bauplan.

A scalable pipeline turning high-volume NetFlow traffic into AI-ready features.

Implement data quality checks using expectations.

Build an interactive dashboard to visualize taxi pickup locations in NYC.