Part 1-3: From Raw Health Text to a Working Retrieval Pipeline

I'm a first-year undergraduate student in Artificial Intelligence Engineering, and this summer I'm building a small RAG (Retrieval-Augmented Generation) project from scratch to learn how these systems actually work under the hood — not just by calling an API, but by building the pipeline piece by piece. This is a log of the first three parts of that journey.

Part 1: Understanding the Building Blocks

Before writing any real project code, I spent time understanding the core ideas behind RAG:

Calling an LLM API: sending a prompt programmatically and getting a response back. I used the Gemini API for this. llm_test.py

Embeddings: the idea that text can be converted into numerical vectors, where semantically similar sentences end up close to each other in vector space. I tested this with a handful of sentences using sentence-transformers and computed cosine similarity between them — it was satisfying to see related sentences actually cluster together numerically. embedding_test.py

Part 1-3: From Raw Health Text to a Working Retrieval Pipeline

Related reading

# Day 5 of learning AI Engineering: built a small RAG app over a PDF

Practical RAG, Part 1: The Simplest RAG That Actually Works

I built a RAG pipeline from scratch, and one wrong answer made me dive even…

I Built a RAG App, Then Asked It What Car I Like. It Didn't Know.

I made a personalized AI web app with RAG

Building a RAG Data Feed: The Ingestion Problems Nobody Warns You About