Ayotomiwa Salau

ChatPDFDoc: A question data answering RAG (Retrieval Augmented Generation) tool

Using Kafka Confluent Python SDK to setup producer and consumer data streams

Datalake presentation talk

Learn how to build and deploy big data jobs to production on AWS EMR with Spark

Building reproducible ML/AI pipelines with MLFlow, Weights and Biases, Hydra and Conda