How should you chunk tables and source code for RAG?
PICTURE THIS: 1, 2, 2, 8
Simple meaning
Keep a table with its header and nearby caption
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
who only read docs from people who shipped.
and tied to GenAI / LLM work.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens step by step?
Before you speak the answer, walk the interviewer through these steps:
- 1Keep a table with
its header and nearby caption
- 2splitting rows from column
names destroys meaning.
- 3For code, keep functions
or classes intact with file path metadata.
- 4OCR and markdown conversion
quality often matter more than the embedder.
- 5Common mistake
What juniors usually get wrong.
- 6Close
When you pick this over the alternative.
EXAMPLE — See it in action
Here's a short line you can speak, broken into clear beats:
Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.
Key takeaway
Keep a table with its header and nearby caption splitting rows from column names destroys meaning.