Skip to content

Commit 16e00a9

Browse files
author
Bob Strahan
committed
Update CHANGELOG.md with custom prompt generator Lambda support for Patterns 2 & 3
1 parent 0cfd9d4 commit 16e00a9

File tree

1 file changed

+11
-0
lines changed

1 file changed

+11
-0
lines changed

CHANGELOG.md

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,10 +5,21 @@ SPDX-License-Identifier: MIT-0
55

66
## [Unreleased]
77

8+
### Added
9+
10+
11+
812
## [0.3.12]
913

1014
### Added
1115

16+
- **Custom Prompt Generator Lambda Support for Patterns 2 & 3**
17+
- Added `custom_prompt_lambda_arn` configuration field to enable injection of custom business logic into extraction processing
18+
- **Key Features**: Lambda interface with all template placeholders (DOCUMENT_TEXT, DOCUMENT_CLASS, ATTRIBUTE_NAMES_AND_DESCRIPTIONS, DOCUMENT_IMAGE), URI-based image handling for JSON serialization, comprehensive error handling with fail-fast behavior, scoped IAM permissions requiring GENAIIDP-* function naming
19+
- **Use Cases**: Document type-specific processing rules, integration with external systems for customer configurations, conditional processing based on document content, regulatory compliance and industry-specific requirements
20+
- **Demo Resources**: Interactive notebook demonstration (`step3_extraction_with_custom_lambda.ipynb`), SAM deployment template for demo Lambda function, comprehensive documentation and examples in `notebooks/examples/demo-lambda/`
21+
- **Benefits**: Custom business logic without core code changes, backward compatible (existing deployments unchanged), robust JSON serialization handling all object types, complete observability with detailed logging
22+
1223
- **Refactored Document Classification Service for Enhanced Boundary Detection**
1324
- Consolidated `multimodalPageLevelClassification` and the experimental `multimodalPageBoundaryClassification` (from v0.3.11) into a single enhanced `multimodalPageLevelClassification` method
1425
- Implemented BIO-like sequence segmentation with document boundary indicators: "start" (new document) and "continue" (same document)

0 commit comments

Comments
 (0)