01
PDF RAG Pipeline
A multimodal retrieval-augmented generation pipeline for exploring ArXiv research papers through natural-language questions and optional image queries.
Projects
From cloud-native platforms and data pipelines to AI-powered applications and computer vision systems.
01
A multimodal retrieval-augmented generation pipeline for exploring ArXiv research papers through natural-language questions and optional image queries.
02
A graph-based streaming analytics system that models NYC Yellow Taxi trips in Neo4j, runs PageRank and breadth-first search, and extends batch ingestion through Kafka and Kubernetes.
03
An automated hourly archive that standardizes public outage data from seven Arizona electric utilities into timestamped JSON snapshots for research and historical analysis.
04
A server-rendered publishing platform modernized with secure authentication, object-level authorization, automated testing, CI, PostgreSQL, and optional Amazon S3 media storage.
05
An end-to-end data-mining study that preprocesses customer data, engineers behavioral and financial features, and compares classical, ensemble, and neural models for churn prediction.
06
A video-processing pipeline that detects and tracks vehicles, associates license plates with each vehicle, reads UK-format plate text, interpolates missed frames, and renders annotated output video.
07
A legacy PHP and MySQL account portal with registration, login, email verification, password recovery, profile updates, and a separate administrative interface.