STEP 01
Find where the answer gets separated
Mark one failing question and its full supporting passage, including headings, conditions, and exceptions. Compare the source with the chunk preview.
- Remove repeated headers and footers only when they are not needed for meaning.
- Prepare clear section boundaries. Check that a forced length split does not separate a rule from its exception.
- Record whether your splitter uses characters or tokens. The answer model's context budget is a separate measurement.
STEP 02
Compare a parent-child baseline
A smaller child passage can match the query while its parent supplies surrounding context. Build a separate test index to compare modes on the same questions.
- Try Paragraph parents aligned with coherent sections. The setup assistant provides trial lengths to start the comparison.
- Inspect the text actually returned by retrieval. A few large parents can still produce a large prompt.
- For questions spanning sections, check that evidence from every required section reaches the answer model. Increasing parent length alone may not solve this.
STEP 03
Test a rule and its exception
Example test design: use a general procedure and a condition that changes one step. Review the answer against both passages.
- Keep one narrow fact question alongside the broad question to detect irrelevant context introduced by larger chunks.
- Compare complete answers and actual input tokens with the same model and prompt.
- Keep some sections out of your tuning questions and validate the chosen settings on those sections too.
Give your changes a fair test.
Open comparison worksheet Use the same questions, inspect the evidence, and record what changed.