Merge branch 'develop' of https://github.com/aws-solutions-library-samples/accelerated-intelligent-document-processing-on-aws into develop

Author: rstrahan

docs/classification.md

@@ -429,6 +429,8 @@ You can mark a class as *excluded* so that downstream stages
 will **skip** sections classified as that class, avoiding wasted LLM
 calls, tokens, and noise in accuracy metrics.
 
+https://github.com/user-attachments/assets/3c5106ee-ffaf-48d0-ac57-6de78a221474
+
 ### How classification decides a section is "excluded"
 
 The **primary mechanism is the LLM classifier** using each class's
@@ -1154,4 +1156,4 @@ classes:
 17. **Use Regex for Known Patterns**: Add regex patterns for document types with predictable content or naming conventions
 18. **Test Regex Thoroughly**: Validate regex patterns against diverse document samples before production use
 19. **Balance Regex Specificity**: Make patterns specific enough to avoid false matches but flexible enough to catch variations
-20. **Monitor Regex Performance**: Track how often regex patterns match vs fall back to LLM classification
+20. **Monitor Regex Performance**: Track how often regex patterns match vs fall back to LLM classification