We've been having issues generating diagrams with Excalidraw that are any degree of complexity. By contrast, LLMs are able to handle Mermaid.js syntax a lot better, as it's much more forgiving and has a simpler declarative style. Refer to https://mermaid.js.org/.
Update so that new diagrams are generated with Mermaid.js, while old diagrams generated with Excalidraw can still be viewed.
Fix for #1082 pushed down adding the `data:image/webp;base64' prefix
of the base64 images to the server image gen API. But the code on the
Obsidian and Desktop client still add these prefixes.
This change stops the Desktop, Obsidian clients from adding the prefix
as it is being handled by the API now. It should resolve showing
images inline in those clients as well
- Translated comments from French to English for better accessibility and understanding.
- Updated CSS comment for loading animation to reflect the change in language.
- Enhanced code readability by ensuring consistent language usage across multiple files.
- Improved user experience by clarifying the purpose of various functions and settings in the codebase.
- Added visual loading indicators to the search modal for improved user experience during search operations.
- Implemented logic to check if search results correspond to files in the vault, with color-coded results for better clarity.
- Refactored the getSuggestions method to handle loading states and abort previous requests if necessary.
- Updated CSS styles to support new loading animations and result file status indicators.
- Improved the renderSuggestion method to display file status and provide feedback for files not in the vault.
- Added a new setting for users to configure the sync interval in minutes, allowing for more flexible automatic synchronization.
- Introduced methods to start and restart the synchronization timer based on the configured interval.
- Updated the synchronization logic to use the user-defined interval instead of a fixed 60 minutes.
- Improved code readability and organization by refactoring the sync timer logic.
- Added a new setting to manage sync folders, allowing users to specify which folders to sync or to sync the entire vault.
- Implemented a modal for folder suggestions to facilitate folder selection.
- Updated the folder list display to show currently selected folders with options to remove them.
- Improved CSS styles for chat interface and folder list for better user experience.
- Refactored code for consistency and readability across multiple files.
- Introduced a new command 'Sync new changes' to allow users to manually synchronize new modifications.
- The command updates the content index without regenerating it, ensuring only new changes are synced.
- User-triggered notifications are displayed upon successful sync.
- Move khoj message border to left like in web ui
- Remove user, sender emojis and name
- Ensure conversation title always at top of chat sessions view,
even if no chat sessions loaded yet, instead of causing layout shift
on chat sessions load
- Track input, output token usage and cost for interactions
via chat api with openai, anthropic and google chat models
- Get usage metadata from OpenAI using stream_options
- Handle openai proxies that do not support passing usage in response
- Add new usage, end response events returned by chat api.
- This can be optionally consumed by clients at a later point
- Update streaming clients to mark message as completed after new
end response event, not after end llm response event
- Ensure usage data from final response generation step is included
- Pass usage data after llm response complete. This allows gathering
token usage and cost for the final response generation step across
streaming and non-streaming modes
