Mastodon Feed
Wrote a Jupyter (cook|note)book that implements a Retrieval Augmented Generation (#RAG) system powered by #Elasticsearch and Gemma #LLM.
Inspired by MongoDB's cookbook (🙇🏻♂️) and mostly done as a learning/scoping exercise, but a twist is my notebook lets you easily toggle between different models and ES-doing-the-data/query-embedding (via ML nodes in your deployment) vs doing all of that yourself when ingesting/querying.