1. Increase support for visual models and multimodal models;
2. The application and workflow can input various multimodal files such as images, documents, audio, and videos.
- Update ShortService and LongService constructors to accept db Session parameter for proper dependency injection instead of using module-level db instance
- Reorganize imports in memory_short_term_controller.py following PEP 8 conventions (stdlib, third-party, local imports)
- Add comprehensive docstrings with type hints to ShortService and LongService methods for better code documentation
- Fix import organization in memory_short_service.py to group related imports and improve readability
- Reorganize imports in user_memory_service.py to follow consistent import ordering patterns
- Update ShortService instantiation in analytics_memory_types to pass db parameter
- Remove module-level db instance initialization in favor of caller-managed database session lifecycle
- Add type annotations to method signatures (end_user_id: str, db: Session, return types)
- Improve code formatting and spacing consistency across memory service files
* [add]Create a workspace and initialize the default ontology engineering scenario
* [add]The language parameters for creating the workspace determine the default language for switching in the ontology project.
* [changes]Standardized return format
* [add]The default ontology is associated with the default configuration.
* [add]Create a workspace and initialize the default ontology engineering scenario
* [add]The language parameters for creating the workspace determine the default language for switching in the ontology project.
* [changes]Standardized return format
* [add]The default ontology is associated with the default configuration.
* [fix]The log retains genuine alerts and errors, while filtering out unnecessary noise.
* [fix]Scenario English and Chinese, emotion specifications
* [fix]Change the "no data" scenario from 0.0 to None
* [fix]The emotional health indicators, emotional advice, and emotional distribution analysis are all linked together.
* [fix]The emotional health indicators, emotional advice, and emotional distribution analysis are all linked together.
* [fix]Separate expected errors from unexpected errors
* [fix]The log retains genuine alerts and errors, while filtering out unnecessary noise.
* [fix]Scenario English and Chinese, emotion specifications
* [fix]Change the "no data" scenario from 0.0 to None