Cost Estimator UI Feature for Context Grouping and Subtotals

Author: Bob Strahan

CHANGELOG.md

@@ -7,6 +7,10 @@ SPDX-License-Identifier: MIT-0
 
 ### Added
 
+- **Cost Estimator UI Feature for Context Grouping and Subtotals**
+  - Added context grouping functionality to organize cost estimates by logical categories (e.g. OCR, Classification, etc.)
+  - Implemented subtotal calculations for better cost breakdown visualization
+
 - **DynamoDB Caching for Resilient Classification**
   - Added optional DynamoDB caching to the multimodal page-level classification service to improve efficiency and resilience
   - Cache successful page classification results to avoid redundant processing during retries when some pages fail due to throttling

lib/idp_common_pkg/idp_common/bedrock/client.py

@@ -78,7 +78,8 @@ def __call__(
         top_k: Optional[Union[float, str]] = None,
         top_p: Optional[Union[float, str]] = None,
         max_tokens: Optional[Union[int, str]] = None,
-        max_retries: Optional[int] = None
+        max_retries: Optional[int] = None,
+        context: str = "Unspecified"
     ) -> Dict[str, Any]:
         """
         Make the instance callable with the same signature as the original function.
@@ -109,7 +110,8 @@ def __call__(
             top_k=top_k,
             top_p=top_p,
             max_tokens=max_tokens,
-            max_retries=effective_max_retries
+            max_retries=effective_max_retries,
+            context=context
         )
 
     def _preprocess_content_for_cachepoint(self, content: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
@@ -177,7 +179,8 @@ def invoke_model(
         top_k: Optional[Union[float, str]] = 5,
         top_p: Optional[Union[float, str]] = 0.1,
         max_tokens: Optional[Union[int, str]] = None,
-        max_retries: Optional[int] = None
+        max_retries: Optional[int] = None,
+        context: str = "Unspecified"
     ) -> Dict[str, Any]:
         """
         Invoke a Bedrock model with retry logic.
@@ -335,7 +338,8 @@ def invoke_model(
             converse_params=converse_params,
             retry_count=0,
             max_retries=effective_max_retries,
-            request_start_time=request_start_time
+            request_start_time=request_start_time,
+            context=context
         )
 
         return result
@@ -346,7 +350,8 @@ def _invoke_with_retry(
         retry_count: int,
         max_retries: int,
         request_start_time: float,
-        last_exception: Exception = None
+        last_exception: Exception = None,
+        context: str = "Unspecified"
     ) -> Dict[str, Any]:
         """
         Recursive helper method to handle retries for Bedrock invocation.
@@ -424,7 +429,7 @@ def _invoke_with_retry(
             response_with_metering = {
                 "response": response,
                 "metering": {
-                    f"bedrock/{converse_params['modelId']}": {
+                    f"{context}/bedrock/{converse_params['modelId']}": {
                         **usage
                     }
                 }
@@ -470,7 +475,8 @@ def _invoke_with_retry(
                     retry_count=retry_count + 1,
                     max_retries=max_retries,
                     request_start_time=request_start_time,
-                    last_exception=e
+                    last_exception=e,
+                    context=context
                 )
             else:
                 logger.error(f"Non-retryable Bedrock error: {error_code} - {error_message}")
@@ -838,6 +844,7 @@ def _sanitize_response_for_logging(self, response: Dict[str, Any]) -> Dict[str,
     top_p: Optional top_p parameter (float or string)
     max_tokens: Optional max_tokens parameter (int or string)
     max_retries: Optional override for the instance's max_retries setting
+    context: Context prefix for metering key (default: "Unspecified")
     
 Returns:
     Bedrock response object with metering information

lib/idp_common_pkg/idp_common/classification/service.py

@@ -770,7 +770,7 @@ def classify_page_sagemaker(
 
                 # Add some metering data for consistency with Bedrock
                 metering = {
-                    "sagemaker/invoke_endpoint": {
+                    "Classification/sagemaker/invoke_endpoint": {
                         "invocations": 1,
                     }
                 }
@@ -910,6 +910,7 @@ def _invoke_bedrock_model(
             top_k=config["top_k"],
             top_p=config["top_p"],
             max_tokens=config["max_tokens"],
+            context="Classification",
         )
 
     def _create_unclassified_result(

lib/idp_common_pkg/idp_common/extraction/service.py

@@ -708,6 +708,7 @@ def process_document_section(self, document: Document, section_id: str) -> Docum
                 top_k=top_k,
                 top_p=top_p,
                 max_tokens=max_tokens,
+                context="Extraction",
             )
 
             total_duration = time.time() - request_start_time

lib/idp_common_pkg/idp_common/ocr/service.py

@@ -284,7 +284,7 @@ def _process_single_page(
         # Extract metering data
         feature_combo = self._feature_combo()
         metering = {
-            f"textract/{self._get_api_name()}{feature_combo}": {
+            f"OCR/textract/{self._get_api_name()}{feature_combo}": {
                 "pages": textract_result["DocumentMetadata"]["Pages"]
             }
         }

lib/idp_common_pkg/idp_common/summarization/service.py

@@ -221,6 +221,7 @@ def _invoke_bedrock_model(
             top_k=config["top_k"],
             top_p=config["top_p"],
             max_tokens=config["max_tokens"],
+            context="Summarization",
         )
 
     def _create_error_summary(self, error_message: str) -> DocumentSummary:

patterns/pattern-1/src/processresults_function/index.py

@@ -549,10 +549,10 @@ def handler(event, context):
 
     # Add metering information
     document.metering = {
-        "bda/documents-custom": {
+        "BDAProject/bda/documents-custom": {
             "pages": custom_pages_count
         },
-        "bda/documents-standard": {
+        "BDAProject/bda/documents-standard": {
             "pages": standard_pages_count
         }
     }

src/ui/src/components/document-panel/DocumentPanel.jsx

@@ -142,8 +142,24 @@ const MeteringTable = ({ meteringData, preCalculatedTotals }) => {
     contextGroups[item.context].push(item);
   });
 
-  // Sort contexts alphabetically and add items with subtotals
-  const sortedContexts = Object.keys(contextGroups).sort();
+  // Sort contexts in specific order: OCR, Classification, Extraction, Summarization
+  const contextOrder = ['OCR', 'Classification', 'Extraction', 'Summarization'];
+  const sortedContexts = Object.keys(contextGroups).sort((a, b) => {
+    const aIndex = contextOrder.indexOf(a);
+    const bIndex = contextOrder.indexOf(b);
+
+    // If both contexts are in the predefined order, sort by their position
+    if (aIndex !== -1 && bIndex !== -1) {
+      return aIndex - bIndex;
+    }
+
+    // If only one context is in the predefined order, it comes first
+    if (aIndex !== -1) return -1;
+    if (bIndex !== -1) return 1;
+
+    // If neither context is in the predefined order, sort alphabetically
+    return a.localeCompare(b);
+  });
 
   sortedContexts.forEach((context) => {
     // Add all items for this context