On November 1st I joined the first RAG cohort from MLOps.Community and went hard for 8 weeks building a proof of concept that combined everything from embedding models, prompting, and retrieval to ranking with a cross encoder to support hybrid search.
I want to extend a public "thank you" to Rahul Parundekar for all his hard work ahead of the long journey, the consistent encouragement and the 1v1 coaching! If anyone needs a machine learning engineer and coach, don't hesitate to get in touch with Rahul.
I put together a succinct version of the final presentation to document my learning, commitments, growth and ultimately to keep me accountable. The entire experience simultaneously energized and propelled me further down the road of machine learning!
The source code is up on Github for anyone who wanted to see the final example with hybrid search.
