You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: CHANGELOG.md
+10-1Lines changed: 10 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,14 +9,23 @@ SPDX-License-Identifier: MIT-0
9
9
10
10
### Added
11
11
12
+
-**Agent Analysis Feature for Natural Language Document Analytics**
13
+
- Added integrated AI-powered analytics agent that enables natural language querying of processed document data
14
+
-**Key Capabilities**: Convert natural language questions to SQL queries, generate interactive visualizations and tables, explore database schema automatically
15
+
-**Secure Architecture**: All Python code execution happens in isolated AWS Bedrock AgentCore sandboxes, not in Lambda functions
16
+
-**Multi-Tool Agent System**: Database discovery tool for schema exploration, Athena query tool for SQL execution, secure code sandbox for data transfer, Python visualization tool for charts and tables
17
+
-**Example Use Cases**: Query document processing volumes and trends, analyze confidence scores and extraction accuracy, explore document classifications and content patterns, generate custom charts and data tables
18
+
-**Sample W2 Test Data**: Includes 20 synthetic W2 tax documents for testing analytics capabilities
19
+
-**Configurable Models**: Supports multiple AI models including Claude 3.7 Sonnet (default), Claude 3.5 Sonnet, Nova Pro/Lite, and Haiku
20
+
-**Web UI Integration**: Accessible through "Document Analytics" section with real-time progress display and query history
21
+
12
22
-**Automatic Glue Table Creation for Document Sections**
13
23
- Added automatic creation of AWS Glue tables for each document section type (classification) during processing
14
24
- Tables are created dynamically when new section types are encountered, eliminating manual table creation
15
25
- Consistent lowercase naming convention for tables ensures compatibility with case-sensitive S3 paths
16
26
- Tables are configured with partition projection for efficient date-based queries without manual partition management
17
27
- Automatic schema evolution - tables update when new fields are detected in extraction results
0 commit comments