- Implemented `getBatchEmbeddings` method in AI module for retrieving embeddings for multiple texts.
- Added vector update methods for messages, files, tasks, projects, and users in ManticoreBase.
- Enhanced ManticoreFile, ManticoreMsg, ManticoreProject, ManticoreTask, and ManticoreUser to support vector generation during sync operations.
- Introduced `generateVectorsBatch` methods for batch processing of vector generation in Manticore modules.
- Updated ManticoreSyncTask to handle incremental updates and vector generation asynchronously.
- Updated AIAssistant to support parsing of additional message links in the format dootask://message/id1/id2.
- Modified search methods in SearchBox to streamline API calls and remove AI search logic, improving performance and clarity.
- Cleaned up unused AI search code and adjusted search result handling for better data presentation.
- Updated documentation to reflect new link formats for tasks, projects, files, and messages.
- Added support for specifying vector dimensions in AI payloads for compatible vendors.
- Updated default AI model from 'text-embedding-ada-002' to 'text-embedding-3-small'.
- Refactored ManticoreBase to bind parameters explicitly for PDO statements, improving type handling.
- Adjusted SQL queries across Manticore modules to remove content previews and ensure inline vector values.
- Updated content preview handling in ManticoreFile, ManticoreProject, ManticoreTask, and ManticoreUser to use substrings for better data management.
- Added session management capabilities to the AI Assistant, allowing users to create, load, and delete sessions.
- Improved modal UI with a new header for session actions and a footer for model selection.
- Updated input handling to support dynamic loading of session data and improved response formatting.
- Enhanced search functionality in various components to utilize the AI Assistant for generating content based on user input.
