Packet To Sniff

Build and evaluate RAG systems

A practical path from the idea of retrieval-augmented generation to a system you can measure and defend. Finish by building a small RAG pipeline yourself.

Intermediate6 stepsFree, no account needed

Steps

  1. Step 1 · 3 min read

    What is retrieval-augmented generation (RAG)?

    The pattern, the pipeline and when to use it.

  2. Step 2 · 3 min read

    How to chunk documents for RAG

    Retrieval can only return what chunking created.

  3. Step 3 · 3 min read

    How vector search works: similarity, top-k and hybrid search

    How the right chunks are found and ranked.

  4. Step 4 · Lab, 45 to 60 minutes

    Build a tiny RAG system in Python

    Build the retrieval half yourself, offline.

  5. Step 5 · 3 min read

    How to evaluate a RAG system: retrieval and answer quality

    Measure instead of guessing.

  6. Step 6 · 3 min read

    Prompt injection in RAG systems and how to reduce it

    Every indexed document is an input.