docs and notebooks update for json schema

Author: kazmer97

docs/assessment.md

@@ -318,9 +318,9 @@ For basic single-value extractions like dates, amounts, or names:
 
 **Configuration:**
 ```yaml
-attributes:
-  - name: "StatementDate"
-    attributeType: "simple"
+properties:
+  StatementDate:
+    type: string
     description: "The date of the bank statement"
 ```
 
@@ -360,14 +360,16 @@ For nested object structures with multiple related fields:
 
 **Configuration:**
 ```yaml
-attributes:
-  - name: "AccountDetails"
-    attributeType: "group"
+properties:
+  AccountDetails:
+    type: object
     description: "Bank account information"
-    groupAttributes:
-      - name: "AccountNumber"
+    properties:
+      AccountNumber:
+        type: string
         description: "The account number"
-      - name: "RoutingNumber"
+      RoutingNumber:
+        type: string
         description: "The bank routing number"
 ```
 
@@ -413,18 +415,22 @@ For arrays of items, such as transactions in a bank statement:
 
 **Configuration:**
 ```yaml
-attributes:
-  - name: "Transactions"
-    attributeType: "list"
+properties:
+  Transactions:
+    type: array
     description: "List of all transactions on the statement"
-    listItemTemplate:
-      itemDescription: "Individual transaction entry"
-      itemAttributes:
-        - name: "Date"
+    x-aws-idp-list-item-description: "Individual transaction entry"
+    items:
+      type: object
+      properties:
+        Date:
+          type: string
           description: "Transaction date"
-        - name: "Description"
+        Description:
+          type: string
           description: "Transaction description"
-        - name: "Amount"
+        Amount:
+          type: string
           description: "Transaction amount"
 ```
 
@@ -979,27 +985,34 @@ attributes:
 Processes complex nested structures as single units:
 ```yaml
 # Each group becomes one focused task
-attributes:
-  - name: "AccountDetails"
-    attributeType: "group"
-    groupAttributes:
-      - name: "AccountNumber"
-      - name: "RoutingNumber"
-      - name: "AccountType"
+properties:
+  AccountDetails:
+    type: object
+    properties:
+      AccountNumber:
+        type: string
+      RoutingNumber:
+        type: string
+      AccountType:
+        type: string
 ```
 
 #### List Item Tasks
 Assesses each list item individually for maximum accuracy:
 ```yaml
 # 100 transactions = 100 individual assessment tasks
-attributes:
-  - name: "Transactions"
-    attributeType: "list"
-    listItemTemplate:
-      itemAttributes:
-        - name: "Date"
-        - name: "Description"
-        - name: "Amount"
+properties:
+  Transactions:
+    type: array
+    items:
+      type: object
+      properties:
+        Date:
+          type: string
+        Description:
+          type: string
+        Amount:
+          type: string
 ```
 
 ### Performance Tuning

docs/classification.md

@@ -602,13 +602,16 @@ When you want all pages of a document to be classified as the same class, you ca
 
 ```yaml
 classes:
-  - name: Payslip
+  - $schema: "https://json-schema.org/draft/2020-12/schema"
+    $id: Payslip
+    x-aws-idp-document-type: Payslip
+    type: object
     description: "Employee wage statement showing earnings and deductions"
     document_name_regex: "(?i).*(payslip|paystub|salary|wage).*"
-    attributes:
-      - name: EmployeeName
+    properties:
+      EmployeeName:
+        type: string
         description: "Name of the employee"
-        attributeType: simple
 ```
 
 **Benefits:**
@@ -632,24 +635,33 @@ classification:
   classificationMethod: multimodalPageLevelClassification
 
 classes:
-  - name: Invoice
+  - $schema: "https://json-schema.org/draft/2020-12/schema"
+    $id: Invoice
+    x-aws-idp-document-type: Invoice
+    type: object
     description: "Business invoice document"
     document_page_content_regex: "(?i)(invoice\\s+number|bill\\s+to|amount\\s+due)"
-    attributes:
-      - name: InvoiceNumber
+    properties:
+      InvoiceNumber:
+        type: string
         description: "Invoice number"
-        attributeType: simple
-  - name: Payslip
+  - $schema: "https://json-schema.org/draft/2020-12/schema"
+    $id: Payslip
+    x-aws-idp-document-type: Payslip
+    type: object
     description: "Employee wage statement"
     document_page_content_regex: "(?i)(gross\\s+pay|net\\s+pay|employee\\s+id)"
-    attributes:
-      - name: EmployeeName
+    properties:
+      EmployeeName:
+        type: string
         description: "Employee name"
-        attributeType: simple
-  - name: Other
+  - $schema: "https://json-schema.org/draft/2020-12/schema"
+    $id: Other
+    x-aws-idp-document-type: Other
+    type: object
     description: "Documents that don't match specific patterns"
     # No regex - will always use LLM
-    attributes: []
+    properties: {}
 ```
 
 **Benefits:**

docs/evaluation.md

@@ -121,19 +121,24 @@ Basic single-value extractions evaluated as individual fields:
 
 ```yaml
 classes:
-  - name: invoice
-    attributes:
-      - name: invoice_number
+  - $schema: "https://json-schema.org/draft/2020-12/schema"
+    $id: invoice
+    x-aws-idp-document-type: invoice
+    type: object
+    properties:
+      invoice_number:
+        type: string
         description: The unique identifier for the invoice
-        attributeType: simple  # or omit for default
-        evaluation_method: EXACT  # Use exact string matching
-      - name: amount_due
+        x-aws-idp-evaluation-method: EXACT  # Use exact string matching
+      amount_due:
+        type: string
         description: The total amount to be paid
-        evaluation_method: NUMERIC_EXACT  # Use numeric comparison
-      - name: vendor_name
+        x-aws-idp-evaluation-method: NUMERIC_EXACT  # Use numeric comparison
+      vendor_name:
+        type: string
         description: Name of the vendor
-        evaluation_method: FUZZY  # Use fuzzy matching
-        evaluation_threshold: 0.8  # Minimum similarity threshold
+        x-aws-idp-evaluation-method: FUZZY  # Use fuzzy matching
+        x-aws-idp-confidence-threshold: 0.8  # Minimum similarity threshold
 ```
 
 ### Group Attributes
@@ -142,30 +147,38 @@ Nested object structures where each sub-attribute is evaluated individually:
 
 ```yaml
 classes:
-  - name: "Bank Statement"
-    attributes:
-      - name: "Account Holder Address"
+  - $schema: "https://json-schema.org/draft/2020-12/schema"
+    $id: BankStatement
+    x-aws-idp-document-type: "Bank Statement"
+    type: object
+    properties:
+      Account Holder Address:
+        type: object
         description: "Complete address information for the account holder"
-        attributeType: group
-        groupAttributes:
-          - name: "Street Number"
+        properties:
+          Street Number:
+            type: string
             description: "House or building number"
-            evaluation_method: FUZZY
-            evaluation_threshold: 0.9
-          - name: "Street Name"
+            x-aws-idp-evaluation-method: FUZZY
+            x-aws-idp-confidence-threshold: 0.9
+          Street Name:
+            type: string
             description: "Name of the street"
-            evaluation_method: FUZZY
-            evaluation_threshold: 0.8
-          - name: "City"
+            x-aws-idp-evaluation-method: FUZZY
+            x-aws-idp-confidence-threshold: 0.8
+          City:
+            type: string
             description: "City name"
-            evaluation_method: FUZZY
-            evaluation_threshold: 0.9
-          - name: "State"
+            x-aws-idp-evaluation-method: FUZZY
+            x-aws-idp-confidence-threshold: 0.9
+          State:
+            type: string
             description: "State abbreviation (e.g., CA, NY)"
-            evaluation_method: EXACT
-          - name: "ZIP Code"
+            x-aws-idp-evaluation-method: EXACT
+          ZIP Code:
+            type: string
             description: "5 or 9 digit postal code"
-            evaluation_method: EXACT
+            x-aws-idp-evaluation-method: EXACT
 ```
 
 ### List Attributes
@@ -174,19 +187,25 @@ Arrays of items where each item's attributes are evaluated individually across a
 
 ```yaml
 classes:
-  - name: "Bank Statement"
-    attributes:
-      - name: "Transactions"
+  - $schema: "https://json-schema.org/draft/2020-12/schema"
+    $id: BankStatement
+    x-aws-idp-document-type: "Bank Statement"
+    type: object
+    properties:
+      Transactions:
+        type: array
         description: "List of all transactions in the statement period"
-        attributeType: list
-        listItemTemplate:
-          itemDescription: "Individual transaction record"
-          itemAttributes:
-            - name: "Date"
+        x-aws-idp-list-item-description: "Individual transaction record"
+        items:
+          type: object
+          properties:
+            Date:
+              type: string
               description: "Transaction date (MM/DD/YYYY)"
-              evaluation_method: FUZZY
-              evaluation_threshold: 0.9
-            - name: "Description"
+              x-aws-idp-evaluation-method: FUZZY
+              x-aws-idp-confidence-threshold: 0.9
+            Description:
+              type: string
               description: "Transaction description or merchant name"
               evaluation_method: SEMANTIC
               evaluation_threshold: 0.7