Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. Retrieval That Still Works at Scale
AI & Machine Learning

Retrieval That Still Works at Scale

Retrieval quality falls as the corpus grows. Chunking, filtering and freshness, and why relevance degrades before anyone notices.

Updated 2 min readBy SpiderHunts Technologies

Free estimateNo obligation

Get a free estimate

Tell us what you need. A senior engineer reads every enquiry.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →

Quick answer — TL;DR

Retrieval that works over a few hundred documents often fails over tens of thousands. Filter before searching, keep the index current, and measure retrieval separately from the final answer.

The short answer

A small corpus hides retrieval problems because almost anything relevant is found. As content grows, near-duplicates and loosely related material crowd out the right answer.

Measure retrieval on its own, because a good final answer can mask poor retrieval right up until it does not.

What degrades as content grows

ProblemEffect
Near-duplicate documentsResults fill with variations of one thing
Outdated versions still indexedConfident answers from superseded content
Chunks too smallContext lost, meaning changes
Chunks too largeRelevant part diluted
No filteringSearching everything, every time

Outdated content is the one that causes real damage. An answer drawn from a superseded policy is worse than no answer, because it is believed.

  1. Narrow by what you already know: tenant, product, date range, permission.
  2. Search within that subset rather than across everything.
  3. Keep structured attributes alongside the text for filtering.
  4. Exclude superseded or archived content by default.
  5. Make the filter part of the query, not a post-processing step.

Point five matters for correctness as well as speed. Filtering afterwards can leave you with nothing when everything retrieved was excluded.

Keep the index current

  • Reindex on change rather than on a slow schedule
  • Remove deleted content promptly
  • Track when each item was last indexed
  • Detect drift between the source and the index
  • Have a way to rebuild from scratch, tested

A stale index produces answers that were right last quarter, and nothing in the output indicates that.

Measure retrieval separately

Keep a set of questions with the documents that should be retrieved for each, and check that they are, independently of what the final answer says.

That separation tells you which half to fix. Without it, a wrong answer could be retrieval, generation or both, and you are guessing.

FAQ

Frequently asked questions

The questions readers ask us after this guide.

Still have a question?

Ask us directly — a senior engineer will get back to you.

Ask about your project

Why does retrieval get worse as content grows?

Near-duplicates and loosely related material crowd out the right answer, which a small corpus hides.

What is the most damaging retrieval problem?

Superseded content left in the index. Answers from it are confident, wrong and believed.

Should filtering happen before or after search?

Before, as part of the query. Filtering afterwards can leave nothing when everything retrieved was excluded.

How do we know whether retrieval or generation is at fault?

Measure retrieval separately, with questions and the documents that should be found for each.

Keep reading

More on AI & Machine Learning

Start here

Running AI in production and hitting limits?

Tell us what the workload looks like and where it hurts: cost, latency, reliability or all three. We will come back with what we would change first and what it would take. No rebuild proposal if a smaller fix will do.

  1. You tell us what you needTwo minutes on the form, or a message on WhatsApp.
  2. A senior engineer reviews itAnd comes back with questions, a realistic range and an honest view on fit.
  3. Free 30-minute scoping callWe talk through scope, options and a realistic estimate — with no obligation.
Free estimateNo obligation

Talk to someone who builds this

Send a short brief and we will come back with an honest view and a realistic range.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →