Update assessment model and document sample references

Author: Bob Strahan

README.md

@@ -73,8 +73,8 @@ After deployment, you can quickly process a document and view results:
    - **Via S3**: Upload directly to the S3 input bucket (find the bucket URL in CloudFormation stack Outputs)
 
 2. **Use Sample Documents**:
-   - For Pattern 1 (BDA): Use [samples/lending_package.pdf](./samples/lending_package.pdf)
-   - For Patterns 2 and 3: Use [samples/rvl_cdip_package.pdf](./samples/rvl_cdip_package.pdf)
+   - For Patterns 1 (BDA) and Pattern 2: Use [samples/lending_package.pdf](./samples/lending_package.pdf)
+   - For Pattern 3 (UDOP): Use [samples/rvl_cdip_package.pdf](./samples/rvl_cdip_package.pdf)
 
 3. **Monitor Processing**:
    - **Via Web UI**: Track document status on the dashboard
@@ -105,8 +105,8 @@ To update an existing GenAIIDP stack to a new version:
 7. For detailed instructions, see the [Deployment Guide](./docs/deployment.md#updating-an-existing-stack)
 
 For testing, use these sample files:
-- Pattern-1 BDA default project: `samples/lending_package.pdf`
-- Patterns 2 and 3 default configurations: `samples/rvl_cdip_package.pdf`
+   - For Patterns 1 (BDA) and Pattern 2: Use [samples/lending_package.pdf](./samples/lending_package.pdf)
+   - For Pattern 3 (UDOP): Use [samples/rvl_cdip_package.pdf](./samples/rvl_cdip_package.pdf)
 
 For detailed deployment and testing instructions, see the [Deployment Guide](./docs/deployment.md).
 

config_library/pattern-2/bank-statement-sample/config.yaml

@@ -381,7 +381,7 @@ assessment:
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  model: us.amazon.nova-pro-v1:0
   system_prompt: >-
     You are a document analysis assessment expert. Your task is to evaluate the confidence of extraction results by analyzing the source document evidence. Respond only with JSON containing confidence scores for each extracted attribute.
   task_prompt: >-

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

@@ -899,7 +899,7 @@ assessment:
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  model: us.amazon.nova-pro-v1:0
   system_prompt: >-
     You are a document analysis assessment expert. Your task is to evaluate the confidence of extraction results by analyzing the source document evidence. Respond only with JSON containing confidence scores for each extracted attribute.
   task_prompt: >-

config_library/pattern-2/rvl-cdip-package-sample/config.yaml

@@ -621,7 +621,7 @@ assessment:
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  model: us.amazon.nova-pro-v1:0
   system_prompt: >-
     You are a document analysis assessment expert. Your task is to evaluate the confidence of extraction results by analyzing the source document evidence. Respond only with JSON containing confidence scores for each extracted attribute.
   task_prompt: >-

config_library/pattern-3/rvl-cdip-package-sample/config.yaml

@@ -481,7 +481,7 @@ assessment:
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  model: us.amazon.nova-pro-v1:0
   system_prompt: >-
     You are a document analysis assessment expert. Your task is to evaluate the confidence of extraction results by analyzing the source document evidence. Respond only with JSON containing confidence scores for each extracted attribute.
   task_prompt: >-

docs/assessment.md

@@ -542,7 +542,7 @@ The assessment service supports configurable image dimensions for optimal confid
 
 ```yaml
 assessment:
-  model: "anthropic.claude-3-5-sonnet-20241022-v2:0"
+  model: "us.amazon.nova-pro-v1:0"
   # Image processing settings - preserves original resolution
   image:
     target_width: ""     # Empty string = no resizing (recommended)

docs/deployment.md

@@ -126,8 +126,8 @@ To update an existing GenAIIDP deployment to a new version:
 1. Open the `S3InputBucketConsoleURL` and `S3OutputBucketConsoleURL` from the stack Outputs tab
 2. Open the `StateMachineConsoleURL` from the stack Outputs tab
 3. Upload a PDF form to the Input bucket (sample files are in the `./samples` folder):
-   - For Pattern-1 BDA default project: use [samples/lending_package.pdf](../samples/lending_package.pdf)
-   - For Patterns 2 and 3 default configurations: use [samples/rvl_cdip_package.pdf](../samples/rvl_cdip_package.pdf)
+   - For Patterns 1 (BDA) and Pattern 2: Use [samples/lending_package.pdf](../samples/lending_package.pdf)
+   - For Pattern 3 (UDOP): Use [samples/rvl_cdip_package.pdf](../samples/rvl_cdip_package.pdf)
 4. Monitor the Step Functions execution to observe the workflow
 5. When complete, check the Output bucket for the structured JSON file with extracted fields
 

lib/idp_common_pkg/idp_common/assessment/README.md

@@ -63,7 +63,7 @@ The assessment service uses configuration-driven prompts and model parameters:
 
 ```yaml
 assessment:
-  model: "anthropic.claude-3-5-sonnet-20241022-v2:0"
+  model: "us.amazon.nova-pro-v1:0"
   temperature: 0
   top_k: 5
   top_p: 0.1

notebooks/examples/config/assessment.yaml

@@ -6,7 +6,7 @@ assessment:
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  model: us.amazon.nova-pro-v1:0
   system_prompt: >-
     You are a document analysis assessment expert. Your task is to evaluate the confidence of extraction results by analyzing the source document evidence. Respond only with JSON containing confidence scores for each extracted attribute.
   

notebooks/examples/config/assessment_granular.yaml

@@ -8,7 +8,7 @@ assessment:
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
+  model: us.amazon.nova-pro-v1:0
   system_prompt: >-
     You are a document analysis assessment expert. Your task is to evaluate the confidence of extraction results by analyzing the source document evidence. Respond only with JSON containing confidence scores for each extracted attribute.