optimize: update assessment configuration for cost efficiency and performance

Author: Bob Strahan

CHANGELOG.md

@@ -49,7 +49,7 @@ SPDX-License-Identifier: MIT-0
   - Maintains backward compatibility for stack updates by keeping the parameter value "default" mapped to the rvl-cdip-sample for pattern-2.
 
 - **Reduce assessment step costs**
-  - Default model for granular assessment is now `us.amazon.nova-pro-v1:0` 
+  - Default model for granular assessment is now `us.amazon.nova-lite-v1:0` - experimentation recommended
   - Improved placement of <<CACHEPOINT>> tags in assessment prompt to improve utilization of prompt caching
 
 ### Fixed

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

@@ -376,7 +376,7 @@ assessment:
     max_workers: "20"
     simple_batch_size: "3"
     list_batch_size: "1"
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   top_p: '0.1'
   max_tokens: '10000'
   top_k: '5'

config_library/pattern-2/lending-package-sample/config.yaml

@@ -915,8 +915,8 @@ classes:
         attributeType: group
 classification:
   image:
-    target_height: '1268'
-    target_width: '951'
+    target_height: ''
+    target_width: ''
   top_p: '0.1'
   max_tokens: '4096'
   top_k: '5'
@@ -1144,19 +1144,19 @@ summarization:
     You are a document summarization expert who can analyze and summarize documents from various domains including medical, financial, legal, and general business documents. Your task is to create a summary that captures the key information, main points, and important details from the document. Your output must be in valid JSON format. \nSummarization Style: Balanced\\nCreate a balanced summary that provides a moderate level of detail. Include the main points and key supporting information, while maintaining the document's overall structure. Aim for a comprehensive yet concise summary.\n Your output MUST be in valid JSON format with markdown content. You MUST strictly adhere to the output format specified in the instructions.
 assessment:
   image:
-    target_height: '1268'
-    target_width: '951'
+    target_height: ''
+    target_width: ''
   granular:
     enabled: true
     max_workers: "20"
     simple_batch_size: "3"
     list_batch_size: "1"
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   top_p: '0.1'
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.amazon.nova-pro-v1:0
+  model: us.amazon.nova-lite-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

@@ -894,12 +894,12 @@ assessment:
     max_workers: "20"
     simple_batch_size: "3"
     list_batch_size: "1"
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   top_p: '0.1'
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.amazon.nova-pro-v1:0
+  model: us.amazon.nova-lite-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

@@ -616,12 +616,12 @@ assessment:
     max_workers: "20"
     simple_batch_size: "3"
     list_batch_size: "1"
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   top_p: '0.1'
   max_tokens: '10000'
   top_k: '5'
   temperature: '0.0'
-  model: us.amazon.nova-pro-v1:0
+  model: us.amazon.nova-lite-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

@@ -476,7 +476,7 @@ assessment:
     max_workers: "20"
     simple_batch_size: "3"
     list_batch_size: "1"
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   top_p: '0.1'
   max_tokens: '10000'
   top_k: '5'

docs/assessment.md

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

lib/idp_common_pkg/idp_common/assessment/README_GRANULAR.md

@@ -72,7 +72,7 @@ The granular service uses the same `task_prompt` template as the original servic
 ```yaml
 assessment:
   # Standard assessment configuration
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   model: us.anthropic.claude-3-7-sonnet-20250219-v1:0
   system_prompt: "Your assessment system prompt..."
   task_prompt: "Your assessment task prompt with <<CACHEPOINT>>..."

notebooks/examples/config/assessment.yaml

@@ -1,7 +1,7 @@
 # Assessment Service Configuration
 # This configuration works with both original and granular assessment approaches
 assessment:
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   top_p: '0.1'
   max_tokens: '10000'
   top_k: '5'

notebooks/examples/config/assessment_granular.yaml

@@ -3,7 +3,7 @@
 # accuracy and scalability when assessing document extraction confidence.
 
 assessment:
-  default_confidence_threshold: '0.9'
+  default_confidence_threshold: '0.8'
   top_p: '0.1'
   max_tokens: '10000'
   top_k: '5'