- Added a new endpoint to fetch community-curated prompts in `search_spaces_routes.py`.
- Enhanced `SetupPromptStep` and `PromptConfigManager` components to display and utilize community prompts.
- Introduced UI elements for selecting and applying prompts, including categories and expandable views.
- Improved state management for selected prompts and custom instructions.
- Added `citations_enabled` and `qna_custom_instructions` fields to the SearchSpace model for better QnA configuration.
- Updated the creation and update schemas to handle new fields with appropriate defaults.
- Refactored QnA handling in the agent to utilize the new SearchSpace fields for improved response customization.
- Adjusted UI components to include settings for managing QnA configurations.
- Enhanced onboarding process to incorporate prompt setup as an optional step.
- Added new LLM providers including Google, Azure OpenAI, Bedrock, and others to the backend.
- Updated the model selection UI to dynamically display available models based on the selected provider.
- Enhanced the provider change handling to reset the model selection when the provider is changed.
- Improved the overall user experience by providing contextual information for model selection.
- Updated the welcome dialog in podcast generation to reflect the correct podcast title.
- Improved the Dashboard layout by adding an indicator for active chats on the researcher page.
- Enhanced the breadcrumb component to fetch and display chat details dynamically.
- Adjusted the chat panel width for better visibility.
- Introduced animations and improved user interactions in the chat panel and podcast player components.
- Updated the ConfigModal to provide clearer instructions for user input.
- Added `validate_llm_config` function to `llm_service.py` for validating LLM configurations via test API calls.
- Integrated validation in `create_llm_config` and `update_llm_config` routes in `llm_config_routes.py`, raising HTTP exceptions for invalid configurations.
- Enhanced error handling to provide detailed feedback on configuration issues.
- Expanded installation options in README to include SurfSense Cloud as a new method.
- Updated UserRead schema to include pages_limit and pages_used fields.
- Added AnnouncementBanner component to the dashboard layout for improved user notifications.
- Refactored DashboardPage to utilize useUser hook for user state management.
- Integrated page usage display in AppSidebar to show user-specific page limits and usage.
- Removed deprecated apiClient code and replaced it with hooks for better API interaction.
- Increased task time limits in celery_app.py for longer processing times.
- Enhanced pagination logic in NotionHistoryConnector to handle large result sets.
- Implemented batch commits every 10 documents across various indexers (Airtable, ClickUp, Confluence, Discord, GitHub, Google Calendar, Gmail, JIRA, Linear, Luma, Notion, Slack) to improve performance and reduce database load.
- Updated final commit logging for clarity on total documents processed.
- Added warning suppression for pdfminer warnings during Docling PDF processing
- Suppresses 'Cannot set gray non-stroke color' warnings that cause uploads to halt
- Temporarily sets pdfminer logger to ERROR level during document processing
- Fixes issue where files ~34MB would fail due to pdfminer warning spam
Resolves issue where PDF uploads would halt with repeated pdfminer warnings
- Modified various FastAPI route definitions to remove trailing slashes for consistency across the application.
- Updated corresponding fetch calls in the frontend to align with the new endpoint structure.
- Ensured that all affected routes maintain their functionality without trailing slashes.
- Integrated ProxyHeadersMiddleware to ensure FastAPI correctly handles HTTPS in redirects when deployed behind a proxy, such as Cloudflare.
- This addition enhances security and proper URL handling in the application.
- Introduced BACKEND_URL in the configuration to allow overriding the HTTP to HTTPS in the OAuth redirect URI.
- Updated the Google OAuth router to conditionally use the BACKEND_URL for the redirect URI when specified.
- Introduced a fixed parameter order for AzureOpenAIEmbeddings to resolve compatibility issues.
- Updated the voice selection logic to include Azure voices in the podcaster utility.
- Modified the page limit service to use a more efficient method for retrieving users.
- Added WindowsProactorEventLoopPolicy for better async subprocess support on Windows.
- Ensured proper cleanup of the event loop after task execution.
- Removed redundant asyncio import from the generate_chat_podcast_task function.
- Added RERANKERS_ENABLED option to control reranking functionality.
- Updated rerank_documents function to handle cases when reranking is disabled.
- Enhanced documentation for environment variables related to rerankers in installation guides.
