INDIA-BASED · INTERNATIONAL DELIVERYsupport@maukaz.com
MAUKAZ — Your Technology Partner
Insights/Knowledge & RAG
PRACTICAL GUIDE · Knowledge & RAG

Choosing how much context to supply

More context can increase cost and distract from the relevant evidence. Select enough material to support the answer without flooding the model with unrelated text.

A practical starting point

Work through these checks in order. Use the results to decide what needs to change in your own workflow.

  1. Measure how many passages are needed for representative questions.
  2. Remove duplicates and preserve useful source labels.
  3. Test complex questions that need multiple documents separately from simple lookups.
ILLUSTRATIVE EXAMPLE

A one-rule question may need one passage, while a comparison may need evidence from several approved documents.

A mistake to avoid

Do not maximize context length simply because the model supports it.

How to check progress

Compare support accuracy, latency and cost at different context budgets.

Your action checklist

Use this checklist while reviewing your own setup. Checkmarks are temporary and stay in this open page.

Need the wider workflow?

This quick note covers one decision. For a worked example, decision table and a fuller implementation workflow, read When retrieval is the right addition to an AI assistant.

Further reading

Official background resources for this topic. The workflow above is general guidance, not a guarantee of a particular result.

AI-assisted editorial content. Examples are illustrative, not client case studies. Read our editorial policy or report a correction.