Select the content types worth stripping from retrieved chunks before injection

Attempt it

Quick reference

TL;DR

Strip scraper chrome (nav, license boilerplate, captions a text model cannot use) but keep titles, code, and cross-references because the model needs them to ground the chunk.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine clipping an article from a magazine for a friend. You cut out the article body, the headline, and any diagrams that matter. You do not also clip the magazine's table of contents, the legal disclaimer at the back, or the page-number footer. Those are part of the physical magazine, not part of the story. Retrieved chunks come with the same problem. The scraper grabs the article body plus a lot of magazine furniture: site navigation, copyright lines, image captions the model cannot see anyway. Strip that furniture before you hand the clipping to the model. But keep the headline and the section heading, those tell your friend what the article is actually about.

Key concepts

Context engineering Retrieval-augmented generation Embeddings

Detailed answer & concept explanation

~3 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

4 minutes: define chrome versus content, walk through the six options with one-line justifications, mention vision vs text only conditional for captions, name an A/B eval pattern to validate a stripping rule.

Real-world examples

Real products, models, and research that use this idea.

LlamaIndex 2026 ships ingestion transformers (e.g. HTMLNodeParser) that remove nav and footer blocks before chunking.
Anthropic's 2026 RAG cookbook for Claude Opus 4.7 explicitly recommends keeping section headings inside each retrieved chunk for citation linkage.
Mozilla's Readability.js, embedded in many production ingest pipelines, is the canonical extract body only library.
Unstructured.io categorizes elements (Title, NarrativeText, FigureCaption, Header, Footer) so ingest can drop categories conditionally.
Cohere's hosted RAG recipes strip cookie banners and repeated nav at ingest and run Cohere Rerank 3.5 on the cleaned text.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you decide whether image captions are chrome or content for your specific stack?

Sign in or go Pro to see the approach for this follow-up.

QWhere should stripping live, ingest or assembly?

Sign in or go Pro to see the approach for this follow-up.

QHow do you catch over-stripping before it ships?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Stripping the section heading along with the navigation. The heading tells the model what topic the chunk is about; nav chrome does not.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.