Spaces:
Build error
Build error
Commit History
-
feat: enhance LLMClient with structured output capabilities
- Introduced structured output handling in LLMClient for both field extraction and unique combinations. - Added methods to create dynamic JSON schemas for structured responses, improving data consistency and usability. - Updated existing methods to utilize the new structured output features, enhancing the overall interaction with the Azure OpenAI API. - Improved logging for better traceability of structured output processing and error handling.c77b1c5
-
feat: enhance app.py with session state management and extraction strategy selection
- Added initialization of session state for field descriptions and unique indices tables to improve user experience. - Implemented a strategy selection feature allowing users to choose between "Original Strategy" and "Unique Indices Strategy" for data extraction. - Updated the configuration section to load and save configurations, enhancing flexibility in managing extraction settings. - Improved logging and error handling throughout the extraction process for better monitoring and debugging.2d87de0
-
feat: enhance architecture and developer documentation for clarity and detail
- Updated ARCHITECTURE.md to provide a comprehensive overview of the multi-agent system, including detailed descriptions of core components and execution flow. - Expanded DEVELOPER.md to include setup instructions, coding standards, error handling, and testing strategies, improving guidance for developers. - Enhanced README.md with detailed features, installation steps, configuration options, and usage examples, ensuring better user understanding of the system. - Added cost tracking and error handling details to documentation, emphasizing the system's robustness and reliability. - Improved logging and debugging information in app.py for better monitoring of costs and execution details.665cc97 -
feat: enhance field and unique indices descriptions handling in app and agents
- Updated app.py to replace YAML text area with a table format for field descriptions, allowing users to input detailed information for each field. - Enhanced FieldMapperAgent to incorporate field descriptions into extraction prompts, improving context for data extraction. - Modified UniqueIndicesCombinator to format unique indices descriptions with additional details such as format, examples, and possible values. - Updated Planner and Executor to include field descriptions in execution plans, ensuring comprehensive context during processing.c1ae600
-
feat: update unique indices combinator to return array of objects
f98e92f
-
Add extraction strategy selection and unique indices handling in app.py and FieldMapperAgent. Enhance Planner to accommodate new parameters for execution plans. Update AzureDIService to process tables and save extracted content in both markdown and JSON formats for improved traceability.
924cb7d
-
Refactor FieldMapperAgent to process entire documents at once, improving efficiency by eliminating page-by-page analysis. Update logging to reflect changes in document processing. Enhance AzureDIService to save extracted content to timestamped files for better traceability.
26b3eb7 -
Refactor AzureDIService to enhance document analysis logging and update table extraction logic. Temporarily disable table extraction and improve content type logging. Update TableAgent to reflect changes in context handling.
Sending back all content and tables in one field, not separated.54478a0
-
Add cost tracking functionality across various components, including Executor, Planner, and FieldMapperAgent. Integrate CostTracker to monitor LLM and document intelligence costs, enhancing logging for cost-related metrics and providing detailed cost breakdowns in the user interface.
966ffcd
-
Update Dockerfile to use new app entry point and enhance requirements.txt with additional dependencies. Remove obsolete streamlit_app.py file.
0a40afa