MODULE 5 · DAY 2
Docs Assistant, Naive RAG
Ground an LLM in your own documents
Gourav Shah · School of DevOps & AI · Hands-on
M5·01
What you'll learn
Five things before you open the lab.
M5·02
1 · The problem: ungrounded answers
M5·03
A model alone can't answer about YOUR docs
Confident, but not about your systems.
M5·04
2 · Anatomy of a GenAI application
M5·05
Four parts make every GenAI app
You already built two of them in M2/M3.
M5·06
3 · The librarian analogy
M5·07
A vector DB shelves by meaning, not title
A filing cabinet needs the exact name.
M5·08
Embeddings: text becomes coordinates
Similar text lands close together.
M5·09
4 · The naive-RAG pipeline
M5·10
Ingest once, then answer every question
Same embedding step, both phases.
M5·11
Where the pieces run
Models native for Metal, everything else in containers.
M5·12
5 · ChromaDB: the lightest vector store
M5·13
ChromaDB, the lightest vector store
Zero-config, under 2 GB, the default here.
M5·14
Wired via environment variables
One service block at a time.
M5·15
6 · Learning Mode: watching the pipeline run
M5·16
Learning Mode, watch the pipeline run
Watch each step happen, live.
M5·17
7 · Where naive RAG breaks
M5·18
Where naive RAG breaks down
It fails in predictable, fixable ways.
M5·19
TO THE LAB
Retrieve, then generate. Stay grounded.
Build it, then watch it ground an answer.
Next: Lab — build the Docs Assistant. · Gourav Shah · School of DevOps & AI
M5·20