Added configuration AutoML in iris-community docker
Examples of serial models

• Youtube demo video
• Article link added

A dashboard for testing out-of-the-box CCDA and FHIR transformations in IRIS. Supports CCD to SDA, FHIR to SDA, and SDA to FHIR testing.

Version 2.0 includes:

• Improved UI dashboard
• Support for FHIR to SDA/SDA to FHIR transformation testing

🚑 Solving critical error on LLM Model config
🐛 Add default model
🧾 PDF file ingestion fix

Key Features
Core Features:

RESTful API for Configuration Management: Facilitates seamless configuration management through a well-structured API.
Secure Storage and Encryption: Ensures that all configurations are securely stored and encrypted.
Configuration Validation: Validates configurations to maintain data integrity and consistency.
Template Management: Allows for the creation and management of configuration templates, enhancing reusability and standardization.
Import/Export Functionality: Supports easy import and export of configurations, enabling efficient data migration and backup.
Audit Logging: Maintains detailed logs of all configuration changes for traceability and compliance.
Performance Monitoring: Continuously monitors system performance to ensure optimal operation.
Advanced Features:

Local LLM Integration with Fallback Support: Integrates local language models with fallback mechanisms to ensure uninterrupted service.
IRIS Database Integration: Provides seamless integration with InterSystems IRIS for efficient healthcare data management.
Redis Caching: Implements Redis caching to enhance performance and reduce latency.
Prometheus Metrics: Utilizes Prometheus for comprehensive metrics collection and monitoring.
Background Tasks: Supports background task processing for asynchronous operations.
Rate Limiting: Implements rate limiting to protect the API from abuse and ensure fair usage.
Role-Based Access Control: Enforces role-based access control to secure sensitive operations and data.
Database Migrations: Facilitates smooth database migrations using Alembic.
API Documentation: Provides thorough API documentation for easy integration and usage.
LLM Features:

Multiple Model Support: Supports multiple language models, including Mistral and Llama2.
Automatic Fallback Mechanisms: Ensures continuous service by automatically falling back to alternative models if needed.
Response Caching: Caches responses to improve performance and reduce load times.
Performance Metrics: Collects and monitors performance metrics for continuous optimization.
Configurable Parameters: Allows for the configuration of various parameters to tailor the system to specific needs.
Local Inference Optimization: Optimizes local inference to enhance performance and reduce resource consumption.
IRIS Integration:

Direct Table Access: Provides direct access to IRIS tables for efficient data management.
Connection Pooling: Implements connection pooling to optimize database connections.
Query Caching: Caches frequent queries to improve performance.
Transaction Support: Ensures data integrity with comprehensive transaction support.
Performance Monitoring: Continuously monitors performance to identify and address bottlenecks.
Error Recovery: Implements robust error recovery mechanisms to ensure system reliability.
Key Improvements
Enhanced Security: Strengthened security measures with secure storage, encryption, and role-based access control.
Improved Performance: Optimized performance through Redis caching, connection pooling, and query caching.
Comprehensive Monitoring: Implemented comprehensive monitoring with Prometheus metrics and performance monitoring.
Robust Error Handling: Enhanced error recovery mechanisms to ensure system reliability and robustness.
Detailed Documentation: Provided thorough API documentation and structured logging for better usability and maintenance.

Key Features and Improvements
Seamless Docker Compose Integration: The project now ensures that all core services, including Frontend, Backend, FHIR Server, PostgreSQL, and InterSystems IRIS, start and operate together seamlessly using Docker Compose. This integration guarantees a smooth and reliable deployment process.

Optimized InterSystems IRIS Integration: We have successfully resolved all startup issues with the IRIS container by fine-tuning environment variables and configurations in the docker-compose.yml file. This enhancement makes the IRIS service a robust and stable component of our containerized deployment.

Resolved Backend Dependencies: All missing Python dependencies, such as PyJWT and shap, have been addressed. This ensures that the backend service operates without any import errors and fully leverages features like rule processing and explainability.

Fixed FHIR Server Database Configuration: The FHIR server's database driver configuration in docker-compose.yml has been corrected to establish a proper connection to the PostgreSQL database, ensuring uninterrupted data flow and storage.

Enhanced Rule Loading Mechanism: The backend's rule loading mechanism has been updated to accurately parse multiple rules defined within a single YAML file. This improvement enhances the flexibility and organization of clinical rules, making the system more adaptable to complex scenarios.

Comprehensive and User-Friendly Documentation: The README.md file has been updated with clear, step-by-step instructions for quick setup using Docker Compose. It also includes a detailed architecture diagram and a well-organized presentation of features and development guidelines, making it easier for users to understand and navigate the project.

Overall, the project is now fully operational, with every function running smoothly and efficiently. This ensures a seamless experience for both developers and end-users.

Minor bug fixes

Added Encounter, Organization and Practitioner CSV data to FHIR Resources

Update module.xml

Updated read me and fixed module namespace issue

Updated READMe and fixed bug that caused frontend API's to be pointed to the wrong endpoint

Key features and improvements include:

1. Robust Docker Compose Setup: Ensured all core services (Frontend, Backend, FHIR Server, PostgreSQL, and InterSystems IRIS) reliably start and run together using Docker Compose.
2. Improved InterSystems IRIS Integration: Resolved critical startup issues with the IRIS container by correcting environment variables and configuration in docker-compose.yml, making the IRIS service a stable component of the containerized deployment.
   Backend Dependency Resolution: Addressed missing Python dependencies, such as PyJWT and shap, ensuring the backend service runs without import errors and can fully utilize features like rule processing and explainability.
3. Corrected FHIR Server Database Configuration: Fixed the FHIR server's database driver configuration in docker-compose.yml to properly connect to the PostgreSQL database.
   Enhanced Rule Loading: Updated the backend's rule loading mechanism to correctly parse multiple rules defined within a single YAML file, improving flexibility and organization of clinical rules.
4. Comprehensive and User-Friendly Documentation: Updated the README.md with clear, step-by-step instructions for quick setup using Docker Compose, a detailed architecture diagram, and a more organized presentation of features and development guidelines.

bug fixes & improvements

Youtube link changed

Added youtube video

Lots of security patches applied by GitHub dependabot.

Project is now docker enabled .

Initial Release

A dashboard for testing out-of-the-box CCDA and FHIR transformations in IRIS. Supports CCD to SDA, FHIR to SDA, and SDA to FHIR testing

Version 2.0.0 Features:

• Improved Dashboard
• Support for FHIR-SDA and SDA-FHIR transformation testing

Initial Release

Initial Release

Initial Release

Initial Release

Initial Release

Initial Release

Initial Release

Initial Release

Initial Release

Make module.xml match Open Exchange version.

Removed unnecessary print statement that caused problems with Embedded Python.

Removed 2.1.HL7 from example exports as that triggered an encoding bug with Embedded Python.