Events / Detroit

MI.NET — Dev J. Shah - Cosine Similarity with Azure AI Search & Azure AI Foundry

Michigan .NET Users Group hosts GenAI evangelist Dev Shah in Southfield for a technical walkthrough of retrieval-augmented generation, covering embeddings and cosine similarity with a live RAG coding demo.

Thu, Sep 24, 9:30 PMEpitec · Southfield · MI

Why it matters

Embedding and retrieval choices directly determine how much context gets stuffed into a prompt, so understanding the mechanics here is a prerequisite for controlling RAG-driven token costs.

The tokenmaxxing angle

Cosine similarity retrieval is the mechanism that decides how much (and how relevant) context an agent pulls into its prompt, making this talk a direct look at one of the biggest levers on RAG token spend.

From the organizers

Speaker Dev Shah live-codes a RAG pipeline in the session, showing embeddings stored in a vector database and retrieved in real time via cosine similarity.