Skip to content

Commit 43f6b60

Browse files
author
Bob Strahan
committed
Update documentation for lending package configuration in Pattern-2
1 parent 6a71279 commit 43f6b60

File tree

2 files changed

+21
-14
lines changed

2 files changed

+21
-14
lines changed

CHANGELOG.md

Lines changed: 14 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,15 @@ SPDX-License-Identifier: MIT-0
77

88
### Added
99

10+
## [0.3.8]
11+
12+
### Added
13+
14+
- **Lending Package Configuration Support for Pattern-2**
15+
- Added new `lending-package-sample` configuration to Pattern-2, providing comprehensive support for lending and financial document processing workflows
16+
- New default configuration for Pattern-2 stack deployments, optimized for loan applications, mortgage processing, and financial verification documents
17+
- Previous `rvl-cdip-sample` configuration remains available by selecting `rvl-cdip-package-sample` for the `Pattern2Configuration` parameter when deploying or updating stacks
18+
1019
- **Text Confidence View for Document Pages**
1120
- Added support for displaying OCR text confidence data through new `TextConfidenceUri` field
1221
- New "Text Confidence View" option in the UI pages panel alongside existing Markdown and Text views
@@ -20,26 +29,31 @@ SPDX-License-Identifier: MIT-0
2029
- Configurable through Web UI without requiring code changes or redeployment
2130

2231
### Changed
32+
2333
- **Converted text confidence data format from JSON to markdown table for improved readability and reduced token usage**
2434
- Removed unnecessary "page_count" field
2535
- Changed "text_blocks" array to "text" field containing a markdown table with Text and Confidence columns
2636
- Reduces prompt size for assessment service while improving UI readability
2737
- OCR confidence values now rounded to 1 decimal point (e.g., 99.1, 87.3) for cleaner display
2838
- Markdown table headers now explicitly left-aligned using `|:-----|:-----------|` format for consistent appearance
39+
2940
- **Simplified OCR Service Initialization**
3041
- OCR service now accepts a single `config` dictionary parameter for cleaner, more consistent API
3142
- Aligned with classification service pattern for better consistency across IDP services
3243
- Backward compatibility maintained - old parameter pattern still supported with deprecation warning
3344
- Updated all lambda functions and notebooks to use new simplified pattern
3445
- Removed fixed image target_height and target_width from default configurations, so images are processed in original resolution by default.
46+
3547
- **Updated Default Configuration for Pattern1 and Pattern2**
3648
- Changed default configuration for new stacks from "default" to "lending-package-sample" for both Pattern1 and Pattern2
3749
- Maintains backward compatibility for stack updates by keeping the parameter value "default" mapped to the rvl-cdip-sample for pattern-2.
50+
3851
- **Reduce assessment step costs**
3952
- Default model for granular assessment is now `us.amazon.nova-pro-v1:0`
4053
- Improved placement of <<CACHEPOINT>> tags in assessment prompt to improve utilization of prompt caching
4154

4255
### Fixed
56+
4357
- **Fixed Image Resizing Behavior for High-Resolution Documents**
4458
- Fixed issue where empty strings in image configuration were incorrectly resizing images to default 951x1268 pixels instead of preserving original resolution
4559
- Empty strings (`""`) in `target_width` and `target_height` configuration now preserve original document resolution for maximum processing accuracy

config_library/pattern-2/lending-package-sample/README.md

Lines changed: 7 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -11,9 +11,9 @@ This directory contains the default-lending configuration for the GenAI IDP Acce
1111

1212
## Validation Level
1313

14-
**Level**: 2 - Comprehensive Testing
14+
**Level**: 2 - Minimal Testing
1515

16-
- **Testing Evidence**: This configuration has been tested with lending sample document including payslips, driver's licenses, bank statements, checks, W2 forms, and insurance applications. It demonstrates robust performance in classifying and extracting detailed financial information from standard lending documents.
16+
- **Testing Evidence**: This configuration has been lightly tested with lending sample document including payslips, driver's licenses, bank statements, checks, W2 forms, and insurance applications.
1717
- **Known Limitations**: Performance may vary with non-standard document formats, heavily redacted financial documents, or documents with poor image quality that affect OCR accuracy.
1818

1919
## Overview
@@ -44,11 +44,10 @@ The configuration defines 6 specialized lending document classes, each with comp
4444
### Classification Settings
4545

4646
- **Model**: Amazon Nova Pro
47-
- **Method**: Text-based holistic classification
47+
- **Method**: Multimodal Page Level Classification
4848
- **Temperature**: 0 (deterministic outputs)
4949
- **Top-k**: 5
5050
- **OCR Backend**: Amazon Textract with LAYOUT, TABLES, and SIGNATURES features
51-
- **OCR Model**: Amazon Claude 3.7 Sonnet for enhanced text extraction and layout understanding
5251

5352
The classification component analyzes document content and structure to accurately identify lending document types and establish proper page boundaries within multi-document packages.
5453

@@ -68,7 +67,7 @@ The extraction component performs comprehensive attribute extraction tailored to
6867

6968
### Assessment Settings
7069

71-
- **Model**: Amazon Claude 3.7 Sonnet
70+
- **Model**: us.amazon.nova-pro-v1:0
7271
- **Granular Assessment**: Enabled with parallel processing
7372
- **Default Confidence Threshold**: 0.9
7473
- **Max Workers**: 20 for improved performance
@@ -77,7 +76,7 @@ Enhanced confidence assessment ensures high accuracy for financial data extracti
7776

7877
### Summarization Settings
7978

80-
- **Model**: Amazon Claude 3.7 Sonnet
79+
- **Model**: us.amazon.nova-premier-v1:0
8180
- **Temperature**: 0 (deterministic outputs)
8281
- **Top-k**: 5
8382

@@ -97,20 +96,14 @@ This configuration is optimized for processing lending document packages that ty
9796

9897
To use this default-lending configuration:
9998

100-
1. **Direct Deployment**: Deploy the GenAI IDP Accelerator with this configuration for lending document processing workflows:
101-
```bash
102-
# Deploy with lending configuration
103-
./deploy.sh --config config_library/pattern-2/default-lending/config.yaml
104-
```
99+
1. **Direct Deployment**: Deploy the GenAI IDP Accelerator with this Pattern-2 configuration for lending document processing workflows.
105100

106101
2. **Loan Processing Integration**: Integrate with existing loan origination systems for automated document processing and data extraction.
107102

108103
3. **Compliance Workflows**: Use for regulatory compliance documentation and audit trail generation.
109104

110105
4. **Custom Lending Workflows**: Adapt for specific lending scenarios:
111-
```bash
112-
cp -r config_library/pattern-2/default-lending config_library/pattern-2/mortgage-processing
113-
```
106+
114107

115108
## Common Customization Scenarios
116109

0 commit comments

Comments
 (0)