- Главная
- Центр помощи
- Журнал изменений
Журнал изменений
Обновитесь до последней версииv1.8.1 - 2024.12.23
- Fixed an issue with DALL-E API requests.
v1.8.0 - 2024.12.22
- Introduced Web Browsing capability. Chatbox AI Models and Gemini 2.0 flash(API) can now be enabled to access real-time internet information, providing responses with cited sources
- Added first-token latency display for message generation, toggleable in settings
- Enhanced image preprocessing capabilities. You can now send images in more formats (e.g., svg, gif) - Chatbox automatically converts them to model-compatible formats and adjusts dimensions to meet model requirements
- Double-click thread title to quickly access the thread list
- Improved compatibility for custom model provider configurations - Chatbox now automatically corrects and handles common configuration errors
- Increased maximum temperature range to 2.0
- Added confirmation for all delete actions
- Updated model list, removing deprecated models
- Various minor bug fixes and improvements
v1.7.0 - 2024.12.01
- Added message branching feature. When regenerating a message, a new branch will be created, allowing you to switch between branches. If you prefer the original behavior, you can choose to expand all branched messages from the branch menu.
- Automatically remembers code block collapse state
- Improved Markdown and code block rendering performance
- Added ability to save a thread as a new conversation
- Multiple file selection now supported when inserting files or images
- On Windows, an exit fullscreen button appears when hovering over the title bar in fullscreen mode
- Added Norwegian and Swedish language support
- Fixed various other issues
v1.6.1 - 2024.11.12
- Added context length and temperature controls in custom provider conversation settings.
- Adjusted the maximum height of the input box. The input area now automatically expands when handling larger amounts of text.
- Added a copy button for Mermaid code blocks.
- Fixed text display issues when rendering complex Mermaid flowcharts.
- Fixed an issue where only images were being inserted when copying content from doc/ppt/xlsx/pdf files.
- Fixed an issue where the floating collapse button below code blocks was overlapping with the horizontal scrollbar.
v1.6.0 - 2024.11.03
- Now you can send web links. Chatbox will automatically fetch webpage content and include it in the chat context. Works with all models.
- Now you can send text files to any models. Chatbox will parse file content locally and include it in the chat context.
- Added collapsible code blocks. Long code blocks in chat history are automatically collapsed (can be disabled in settings).
- Redesigned image preview window.
- Redesigned SVG image preview and save functionality.
- Redesigned Mermaid diagram preview and save functionality.
- Improved auto-scroll behavior: auto-scroll stops when generated message fills the screen for better readability.
- Optimized overall app layout and spacing.
- Auto-fetch model options from remote
- Support sending attachments (images/links/files) without text
- Fixed language preference issues in auto-generated titles.
- Fixed data issues when editing messages in copied conversations.
- Fixed drawer direction issues in Arabic.
v1.5.1 - 2024.10.09
- Fixed an issue on Windows where multiple application instances could be launched, causing duplicate icons in the system tray
- On macOS, System Events permission is now only requested when enabling the "launch at startup" option, rather than automatically requesting it when the application starts
- Fixed an issue where automatically generated titles were occasionally truncated
v1.5.0 - 2024.10.05
- Added system tray icon, optimized show/hide shortcut
- Input box now supports direct drag-and-drop insertion of images or files
- Added option for launch at system startup (disabled by default, can be enabled in settings)
- Added thread title menu for quick thread switching and deletion
- Added toggle for automatic title generation to save tokens when disabled
- Added Italian language support
- Gemini and Groq models now support fetching the latest model lists remotely
- Gemini models now support sending images by default
- Ollama models now support sending images by default
- Updated model lists for various model providers
- Improved mobile experience, fixed issue with excessive bottom space after keyboard pop-up
v1.4.2 - 2024.09.13
- Added support for new o1 model series
- SVG image previews are now available
- Fixed display bugs with Artifact previews
- Fixed various minor bugs
v1.4.1 - 2024.09.04
- Chatbox AI service users can now choose from a wider range of models
- Added Arabic language support (العربية)
- Improved LaTeX styling
- Fixed a rare issue that could cause data loss
- Various minor bug fixes and improvements
v1.4.0 - 2024.08.18
- Added Mermaid chart preview, now you can preview AI-generated charts, flowcharts, mind maps, etc.
- Added quick buttons to switch between models
- Now you can add model options for custom models
- Updated model lists for various providers
- Added support for sending images when connecting to ollama's llava model
- After changing avatars, you can now revert to the default avatar
- Added support for Spanish and Portuguese languages
- Fixed several known minor issues
v1.3.16 - 2024.07.22
- Add support for new model API
v1.3.15 - 2024-07-17
- Introduced Artifact Preview feature: Now you can preview HTML code (including JS, CSS, and TailwindCSS) within generated messages.
- Added pop-up mode for Artifact Preview.
- New toggle in Settings to enable automatic Artifact rendering.
- Enhanced chat UI for a more visually appealing experience.
- Optimized message generation performance.
- Resolved known issues with app update notifications.
- Resolved connection issues with Ollama on the Android version.
- Enhanced compatibility with older Android OS versions.
- Fixed several known bugs.
v1.3.14 - 2024.06.30
- Added support for setting user and assistant avatars.
- Fixed some API compatibility issues with custom model providers.
- Resolved various known bugs.
v1.3.13 - 2024.06.23
- Add support for new model
- Fixed some known issues
v1.3.12 - 2024.06.11
- Added support for an unlimited number of custom model providers, allowing for easy integration and switching between various API-compatible models.
- Enhanced the keyboard experience on mobile devices.
- Fixed several minor known issues.
v1.3.10 - 2024.05.15
- Added support for the new model
v1.3.9 - 2024-05-14
- Added support for the new model.
- Refined the UI for global message search.
- Image detail window now supports image zoom.
- Enhanced various other UI details.
v1.3.6 - 2024.05.04
New Features:
- Enhanced conversation-specific settings with an easy-to-use interface for modifying system prompts.
- Added the ability to export chat logs from conversations in various formats including HTML, TXT, and MD.
- Introduced image sending capabilities for Custom Models.
- Integrated support for Groq.
Improvements:
- Implemented automatic collapsing of lengthy system prompts with an option for manual expansion.
- Reworked conversation-specific settings with a new button to revert to global defaults.
- Adjusted the maximum width of message bodies for an improved reading experience, with a toggle button for width adjustments.
- Optimized the display performance of floating menus and button groups.
Fixes:
- Fixed an issue where spaces could not be entered when creating a copilot.
- Addressed display issues for messages with very low height.
Miscellaneous:
- After switching between historical topics, the message list now automatically scrolls to the bottom.
- Enabled access to local Ollama services within the Chatbox web version.
v1.3.5
- Fixed a bug where text copied from Microsoft Word was inserted as an image.
v1.3.4
- You can now send files to AI, with support for PDF, DOC, PPT, XLS, TXT, and code files.
- The input box now allows you to insert images and files from the system clipboard.
- Added support for auto-generating thread titles.
- You can change the installation path during setup in Windows.
- Made some UI detail adjustments.
v1.3.3
- You can now set user avatars in messages.
- Implemented an option in settings to enable or disable Markdown and LaTeX rendering.
- Fixed issues with LaTeX rendering.
- Fixed potential stuttering and crashing issues during message generation.
- Fixed issues with redundant pop-up prompts during auto-updating.
- Fixed various minor bugs.
v1.3.1
- Fixed a bug that caused blank text blocks to appear in model requests.
- Fixed the auto-scroll bug in the message list that occurred when editing past messages.
v1.3.0
- Introducing Vision feature: You can now send images to AI!
- A complete redesign of the app layout for a fresh and intuitive user experience.
- Added message timestamps
- Fixed some known minor issues
v1.2.6
- Added new model series for version 0125.
- Optimized mobile adaptation for some dialogs.
v1.2.4
- You can now use the ⬆️⬇️ arrow keys in the input field to select and quickly enter previous messages.
- Fixed the spell check feature, which can now be turned off in settings.
- Text copied from Chatbox will be copied to the clipboard as plain text without background color — a longstanding minor bug that has finally been resolved.
v1.2.2
- Thread Archiving (refreshes context) and Thread History List.
- Introduced support for the Ollama, enabling easy access to locally deployed models such as llama2, mistral, mixtral, codellama, vicuna, yi, and solar.
- Fixed an issue where the fullscreen window would not restore to fullscreen on the second launch.
v1.2.1
- Redesigned the message editing dialog
- Fixed an issue where token configurations could not be saved
- Fixed the positioning issue with newly copied conversations
- Simplified the tips in settings
- Optimized some interaction issues
- Fixed several other issues
v1.2.0
- Added an image generation feature (Image Creator); you can now generate images within Chatbox, powered by the Dall-E-3 model.
- Improved some usability issues.
v1.1.4
- Added direct support for the 1106 model series.
- Updated the method for calculating message tokens to be more accurate.
- Introduced the Top P parameter option.
- The temperature parameter now supports two decimal places.
- The software now retains the last conversation upon startup.
v1.1.2
- Optimized the interaction experience of the search box
- Fixed the scrolling issue with new messages
- Fixed some network related issues
v1.1.1
- Fixed an issue where message content cannot be selected during generation process
- Improved the performance of the search function, making it faster and more accurate
- Adjusted the layout style of messages
- Fixed some other minor issues
v1.1.0
- Now you can search messages from current chat or all chats
- Data backup and restore (data import/export)
- Fixed some minor issues
v1.0.4
- Keep the previous window size and position upon startup (#30)
- Hide the system menu bar (for Windows, Linux)
- Fixed an issue with session-specific settings causing license and other settings abnormalities (#31)
- Adjusted some UI details
v1.0.2
- Automatically move cursor to the bottom of the input box when quoting a message.
- Fixed the issue of resetting context length setting when switching models (#956).
- Automatically compatible with various Azure Endpoint configurations (#952).
v1.0.0
- Support custom models (#28)
- The up arrow key can quickly input the previously sent message.
- Added x64 and arm64 architecture versions to Windows and Linux installation packages.
- Fixed issue in session settings of Azure model where the model deployment name could not be modified (#927).
- Fixed issue with inability to enter spaces and line breaks when modifying default prompt (#942).
- Fixed scrolling issue after editing long messages.
- Fixed various other minor issues.
v0.6.7
- Action buttons on messages now remain visible during list scrolling
- Language support expanded to include more countries
- Fixed some minor issues
v0.6.5
- Added application shortcuts for quickly showing/hiding windows, switching conversations, etc. See the settings page for details.
- Introduced a new setting for the maximum amount of context messages, allowing more flexible control of the context message count and saving token usage.
- Added support for 0301 and 0314 model series.
- Added a temperature setting in the conversation special settings.
- Fixed some minor issues.
v0.6.3
- Added support for modifying model settings for each conversation (this allows different sessions to use different models)
- Optimized performance when handling large amounts of data
- Made the UI more compact
- Fixed several minor issues
v0.6.2
- Added bulk cleaning feature for conversation lists
- Support for displaying token usage of messages
- Support for modifying the default prompt for new conversations
- Support for setting smaller font sizes
- Fixed a few other minor issues
v0.6.1
- Improved software stability and performance
- More user-friendly error messages
- Use system language during initialization
- Fixed occasional installation errors and white screen issues on Windows
- Fixed compatibility issues related to configuration saving on MacOS 10
- Fixed performance issues on Linux
- Fixed network issues with API Host when using the HTTP protocol
v0.5.6
- Improved window selection strategy for message contexts
- Enhanced settings for message context and generated message max tokens
- Fixed some minor issues
v0.5.2
- Fix settings saving issue on Windows 11
- Optimize loading animation for message generation
- Resolve some other issues
v0.5.1
- Fixed the issue of saving settings in Windows 11
v0.5.0
- Built-in AI service "Chatbox AI" - ready to use out of the box with fast, hassle-free setup.
- Fixed the issue where the night theme would not work after restarting
- Fix the issue of being unable to switch sessions while generating answers
- Fixed lag issues when editing messages
- Fixed issues with conversation name changes and cleared messages reappearing after clearing messages
- Fixed several other minor issues
0.4.5
- Added "My Copilots" feature 🚀🚀🚀
- A large number of AI copilots are ready to work with you
- You can also create your own AI copilot through prompts
- Added support for ChatGLM-6B
- Fixed some known minor issues
v0.4.4
- Added support for Microsoft Azure model API
- Fixed some minor known issues