Merge branch 'develop' v0.4.7

Author: Bob Strahan

CHANGELOG.md

@@ -5,6 +5,36 @@ SPDX-License-Identifier: MIT-0
 
 ## [Unreleased]
 
+## [0.4.7]
+
+### Added
+
+- **MCP Integration Cross-Region Support for QuickSuite Integration**
+  - Added cross-region support for QuickSuite integration enabling MCP connectivity across multiple AWS regions: us-east-1, us-west-2, eu-west-1, ap-southeast-2
+
+### Fixed
+
+- **Stack deployment failure due to MCP Integration IAM Permissions - [GitHub Issue #154](https://github.com/aws-solutions-library-samples/accelerated-intelligent-document-processing-on-aws/issues/154)**
+  - Fixed missing permissions in AgentCoreGatewayManagerFunctionRole by creating the AgentCoreGateway execution role explicitly in the CloudFormation template instead of dynamically in the Lambda function
+
+- **Post-Processing Lambda Hook Compression Handling - [GitHub Issue #155](https://github.com/aws-solutions-library-samples/accelerated-intelligent-document-processing-on-aws/issues/155)**
+  - Added intermediate decompression lambda to handle document decompression before invoking custom post-processing lambdas
+  - **Root Cause**: After introducing document compression, the post-processing lambda hook was receiving compressed documents in the EventBridge payload, forcing external lambdas to import `idp_common` package and handle decompression manually
+  - **Solution**: New `PostProcessingDecompressor` lambda function intercepts EventBridge events, decompresses documents using `Document.load_document()`, and invokes custom post-processors with decompressed payload
+  - **Benefits**: Maintains backward compatibility, eliminates external dependencies (no `idp_common` import needed), keeps compression/decompression logic encapsulated within IDP stack, minimal performance impact (<1s latency)
+
+- **Enhanced Bedrock Error Handling for Agent Companion Chat**
+  - Implemented robust error handling system for Bedrock API errors in Agent Companion Chat feature with automatic retry and graceful degradation
+  - **Automatic Retry with Exponential Backoff**: Configured boto3 with adaptive retry mode (3 attempts) and exponential back-off to prevent service overload
+  - **User-Friendly Error Messages**: Created `BedrockErrorMessageHandler` to convert technical errors into clear, actionable messages for service unavailable (503), throttling (429), access denied (403), validation errors (400), timeouts (408), and quota exceeded scenarios
+  - **Sub-Agent Error Handling**: When sub-agents (Analytics, Error Analyzer, Code Intelligence) encounter Bedrock errors, the orchestrator continues gracefully without crashing, only displaying the first error to avoid duplicates while allowing other sub-agents to complete
+
+### Templates
+   - us-west-2: `https://s3.us-west-2.amazonaws.com/aws-ml-blog-us-west-2/artifacts/genai-idp/idp-main_0.4.7.yaml`
+   - us-east-1: `https://s3.us-east-1.amazonaws.com/aws-ml-blog-us-east-1/artifacts/genai-idp/idp-main_0.4.7.yaml`
+   - eu-central-1: `https://s3.eu-central-1.amazonaws.com/aws-ml-blog-eu-central-1/artifacts/genai-idp/idp-main_0.4.7.yaml`
+
+
 ## [0.4.6]
 
 ### Added

VERSION

@@ -1 +1 @@
-0.4.6
+0.4.7

config_library/pattern-2/rvl-cdip-package-sample-with-few-shot-examples/config.yaml

@@ -96,7 +96,7 @@ classes:
               "cc": null,
               "reference_number": "TNJB 0008497"
         imagePath: >-
-          config_library/pattern-2/few_shot_example_with_multimodal_page_classification/example-images/letter1.jpg
+          config_library/pattern-2/rvl-cdip-package-sample-with-few-shot-examples/example-images/letter1.jpg
       - classPrompt: This is an example of the class 'letter'
         name: Letter2
         attributesPrompt: |-
@@ -112,7 +112,7 @@ classes:
               "cc": null,
               "reference_number": null
         imagePath: >-
-          config_library/pattern-2/few_shot_example_with_multimodal_page_classification/example-images/letter2.png
+          config_library/pattern-2/rvl-cdip-package-sample-with-few-shot-examples/example-images/letter2.png
   - $schema: https://json-schema.org/draft/2020-12/schema
     $id: form
     x-aws-idp-document-type: form
@@ -587,7 +587,7 @@ classes:
               "thread_id": null,
               "message_id": null
         imagePath: >-
-          config_library/pattern-2/few_shot_example_with_multimodal_page_classification/example-images/email1.jpg
+          config_library/pattern-2/rvl-cdip-package-sample-with-few-shot-examples/example-images/email1.jpg
   - $schema: https://json-schema.org/draft/2020-12/schema
     $id: questionnaire
     x-aws-idp-document-type: questionnaire
@@ -805,7 +805,7 @@ classes:
               "account_number": ["003525801543","352580154336"],
               "transactions": [{"Date": "2/6/2020", "Description": "Food Purchase - AnyCompany Restaurant - 1194989245", "Amount": "-171"}]
         imagePath: >-
-          config_library/pattern-2/few_shot_example_with_multimodal_page_classification/example-images/bank-statement-pages/
+          config_library/pattern-2/rvl-cdip-package-sample-with-few-shot-examples/example-images/bank-statement-pages/
 
 classification:
   maxPagesForClassification: "ALL"
@@ -823,9 +823,9 @@ classification:
     You are a multimodal document classification expert that analyzes business documents using both visual layout and textual content. Your task is to classify single-page documents into predefined categories based on their structural patterns, visual features, and text content. Your output must be valid JSON according to the requested format.
 
     <variables>
-    DOCUMENT_TEXT: OCR-extracted text content from the document page that provides textual information for classification
-    DOCUMENT_IMAGE: Visual representation of the document page that provides layout, formatting, and visual structure information
-    CLASS_NAMES_AND_DESCRIPTIONS: List of valid document types with their descriptions that the document must be classified into
+    <document-ocr-data>: OCR-extracted text content from the document page that provides textual information for classification
+    <document-image>: Visual representation of the document page that provides layout, formatting, and visual structure information
+    <document-types>: List of valid document types with their descriptions that the document must be classified into
     </variables>
   task_prompt: >-
     <reasoning-guidelines>
@@ -837,6 +837,10 @@ classification:
     - Provide specific evidence from both visual and textual analysis
     </reasoning-guidelines>
 
+    <document-types>
+    {CLASS_NAMES_AND_DESCRIPTIONS}
+    </document-types>
+
     <output-format>
     Return your classification as valid JSON following this exact structure:
     {
@@ -893,6 +897,11 @@ extraction:
 
     </task>
 
+    <few-shot-examples>
+
+    {FEW_SHOT_EXAMPLES}
+
+    </few-shot-examples>
 
     <extraction-guidelines>
 

docs/deployment.md

@@ -104,6 +104,9 @@ idp-cli deploy \
 
 ## Option 3: Build Deployment Assets from Source Code
 
+Demo Video (5 minutes)
+
+
 ### Dependencies
 
 You need to have the following packages installed on your computer: