Fixes typo in directory name and updates all import paths:
- Renamed surfsense_backend/app/retriver/ to surfsense_backend/app/retriever/
- Updated imports in db.py
- Updated imports in connector_service.py
- Added streaming service support to the Q&A agent for real-time token streaming.
- Updated `answer_question` method to stream responses token-by-token to the frontend.
- Modified `handle_qna_workflow` to handle both custom and values streaming modes.
- Enhanced state management to include streaming service for improved user experience.
- Replaced direct localStorage token access with a centralized `getBearerToken` function across various components and hooks to improve code maintainability and security.
- Updated API calls to use `authenticatedFetch` for consistent authentication handling.
- Enhanced user experience by ensuring proper redirection to login when authentication fails.
- Cleaned up unused imports and improved overall code structure for better readability.
- Replaced the completion step component with a more streamlined onboarding page that includes action cards for managing teams, adding sources, and starting chats.
- Updated the search space form to make the description field optional and improved validation messages.
- Adjusted the onboarding logic to support auto-configuration of LLM roles and improved loading states.
- Removed unused imports and components to clean up the codebase.
- Changed the API URL in the DashboardBreadcrumb component to include search space ID for fetching editor content, ensuring correct context is used when accessing documents.
- Simplified the RowActions component by removing unused imports and replacing the dropdown menu with tooltip buttons for editing, viewing metadata, and deleting documents.
- Updated the JsonMetadataViewer component to support controlled mode for better integration with the RowActions component.
- Adjusted CSS variables for destructive actions in globals.css for improved visual consistency.
- Modified API endpoints to include search space ID in the URL for fetching and saving documents.
- Added permission checks for reading and updating documents based on search space.
- Updated the document saving endpoint to trigger reindexing after saving.
- Introduced a new Celery task for reindexing documents.
- Refactored the editor page to reflect the changes in the API endpoint and method.
