- Added configuration for enabling cross-tenant access in the application.
- Introduced new API endpoints for listing and searching tenants, accessible only to users with the appropriate permissions.
- Updated user and tenant models to include the `can_access_all_tenants` field.
- Enhanced the authentication middleware to handle cross-tenant requests and validate user permissions.
- Created a new TenantSelector component for selecting tenants in the frontend, improving user experience.
- Updated internationalization files to support new tenant-related strings and messages.
- Migrate web search result conversion logic to a new searchutil package to avoid code duplication and improve maintainability.
- Implement robust keyword score normalization using percentile bounds in the searchutil package, enhancing score handling across different contexts.
- Update relevant functions in the application to utilize the new searchutil methods, streamlining the codebase.
- Enhanced Elasticsearch query construction by safely building the query body using JSON marshaling, improving error handling for query parsing and marshaling.
- Updated JWT secret retrieval to securely generate a random secret if the environment variable is not set, ensuring better security practices.
- Updated the Input-field component to improve styling and consistency with new color scheme.
- Added model recommendation section in AgentSettings with localized content for better user guidance.
- Enhanced AgentStreamDisplay to conditionally show timeline based on event types, improving user experience.
- Updated botmsg and docInfo components for better display of web search references and document information.
- Improved fallback response handling in session management, allowing for more flexible user interactions.
- Introduced deduplication and scoring mechanisms in grep_chunks and knowledge_search tools to enhance search result relevance and diversity.
- Updated chunk repository methods to support deletion of unindexed chunks and listing all FAQ chunks by knowledge ID.
- Introduced batch update functionality for chunks in the chunk service.
- Enhanced FAQ import logic to handle append and replace operations, improving efficiency and data integrity.
- Added content hash calculation for FAQ entries to facilitate quick matching and deduplication.
- Refactored related methods to streamline the import process and improve logging for better tracking of import tasks.
- Updated the `uploadKnowledgeFile` function to accept an optional progress callback, enabling real-time upload progress tracking.
- Refactored the document upload handling in the menu component to support multiple file uploads with individual progress events.
- Removed deprecated document processing state management from the KnowledgeBase view, streamlining the upload process.
- Improved user feedback during file uploads by dispatching events for upload start, progress, and completion.
- Added support for tracking the status of FAQ import tasks, including progress indicators for ongoing imports.
- Introduced new localization strings for processing tasks and batch operations in multiple languages.
- Updated the FAQ entry manager to display import progress and improved user feedback during the import process.
- Enhanced the KnowledgeBase component to reflect the processing state of knowledge items, improving user experience during document uploads.
- Implemented batch deletion functionality for chunks, streamlining the management of knowledge base content.
- Added a new menu item for searching FAQs directly from the menu, improving user accessibility.
- Implemented batch action options for selected FAQs, allowing users to perform bulk operations such as enabling, disabling, and deleting entries.
- Updated localization strings to support new features and improve user experience across multiple languages.
- Enhanced the handling of FAQ selection changes to dynamically update the UI based on user interactions.
- Eliminated the 'isDefault' field from model settings and related service logic, simplifying model management.
- Updated UI components to remove references to default models, ensuring a cleaner user experience.
- Adjusted backend model creation and update processes to reflect the removal of default model selection logic.
- Eliminated the check for the 'enabled' field in the ValidateConfig method of agentService.
- Updated comments in session service to reflect the removal of the 'enabled' field from AgentConfig.
- Streamlined agent configuration handling for improved clarity and maintainability.
- Updated the logging message for Neo4j configuration to a warning level when not enabled.
- Removed unused environment variable checks related to graph RAG processing.
- Enhanced the chunk extraction task creation logic to respect the new extract configuration settings.
- Added an `Enabled` field to the ExtractConfig struct for better configuration management.
- Introduced new localization strings for document count, FAQ entries, and chunk count in English, Russian, and Chinese.
- Updated the KnowledgeBase and KnowledgeBaseList components to display knowledge and chunk counts.
- Implemented backend functions to count knowledge items and chunks associated with each knowledge base, improving data management and user insights.
- Replaced `vlm_model_id` with a structured `vlm_config` object in knowledge base configurations, including `enabled` flag and `model_id`.
- Updated API documentation to reflect changes in VLM configuration structure.
- Enhanced frontend interfaces to accommodate new VLM configuration format.
- Improved localization for new features related to knowledge graph and multimodal capabilities.
- Implemented a function to retrieve reasons for agent unavailability, enhancing user feedback on configuration issues.
- Updated the agent status message to include specific missing configurations, improving clarity for users.
- Enhanced localization support for new messages related to agent configuration requirements in English, Russian, and Chinese.
- Added navigation options for users to quickly access model configuration settings when the agent is not ready.
- Removed the `thinkingModelId` and `rerankModelId` from agent configuration, streamlining the settings structure.
- Introduced a new `conversationModels` interface to manage summary and rerank model IDs.
- Updated related UI components and API logic to accommodate the changes in agent configuration.
- Enhanced localization for new conversation model settings in English, Russian, and Chinese.
wizardchen