pygpt-net 2.1.37__py3-none-any.whl → 2.4.48__py3-none-any.whl

pygpt_net/CHANGELOG.txt

@@ -1,3 +1,804 @@
+2.4.48 (2025-01-16)
+
+- Fix: parsing lists in data loaders configuration.
+- Fix: crash on Windows on PySide6 v6.6.0.
+- Added Gemini embeddings to LlamaIndex settings.
+- LlamaIndex upgraded to 0.12.11.
+- Security updates.
+
+2.4.47 (2025-01-14)
+
+- Added support for Python 3.12.
+- Added a new model to Chat with Files: gemini-2.0-flash-exp.
+- PySide6 upgraded to 6.6.0.
+
+2.4.46 (2024-12-16)
+
+- Added a new tab in Settings: "API Keys", where the API keys configuration for Google and Anthropic models has been relocated.
+- Introduced a new mode in "Chat with Files": "Retrieve Only", which allows for retrieving raw documents from the index.
+- Fixed a bug related to tool calls in the Gemini provider when using Chat with Files mode.
+
+2.4.45 (2024-12-16)
+
+- Enhanced web data loaders UI.
+
+2.4.44 (2024-12-16)
+
+- Enhanced web data loaders.
+- Web loaders have been added to attachments, allowing external web content to be attached to context via the "+Web" button in the Attachments tab.
+- Improved handling of attachments in groups and added an attachment icon when a group contains attachments.
+
+2.4.43 (2024-12-15)
+
+- Fix: Bug on attachment upload.
+- Added: Attachments uploaded in groups are now available for all contexts in the group (beta).
+
+2.4.42 (2024-12-15)
+
+- Added Mailer plugin, which allows sending and retrieving emails from the server, and reading them. It currently supports only SMTP.
+- Added 'web_request' command to the Web Search plugin, enabling GET/POST/PUT and other connections to any address and API endpoint. It also supports sending POST data, files, headers, cookies, and more.
+- Improved audio output.
+- Enhanced visibility of the Video menu.
+- Other fixes.
+
+2.4.41 (2024-12-14)
+
+- Improved switching between columns on a split screen.
+- Added visual identification of the active column.
+
+2.4.40 (2024-12-13)
+
+- Enhanced Split Screen mode, now promoted from beta to stable.
+- Python Code Interpreter tool added to the Tabs.
+- HTML/JS Canvas tool added to the Tabs.
+- Added attachment icon to the context list if context has attachments.
+- Improved audio playback.
+- Improved web search.
+- Added a thumbnail image to web search results.
+- Added a new commands to web search: "extract_images" and "extract_links".
+- Added the option "Use raw content (without summarization)" to the web search plugin, which provides a more detailed result to the main model.
+- Extended the default maximum result characters to 50,000 in the web search plugin.
+
+2.4.39 (2024-12-09)
+
+- Added "Split Screen" mode (accessible via the switch in the bottom-right corner of the screen), which allows you to work in two windows simultaneously. It is currently experimental (beta). Future updates will include Code Interpreter and Canvas running in tabs.
+
+- Fixed: Language switch.
+
+2.4.38 (2024-12-08)
+
+- Added the ability to select a style for chat display between: Blocks, ChatGPT-like, and ChatGPT-like Wide. New option in the menu: Config -> Theme -> Style...
+- Added configuration options for audio input in Settings -> Audio -> Audio Input Device, Channels, and Sampling rate.
+
+2.4.37 (2024-11-30)
+
+- The `Query only` mode in `Uploaded` tab has been renamed to `RAG`.
+- New options have been added under `Settings -> Files and Attachments`: 
+  - `Use history in RAG query`: When enabled, the content of the entire conversation will be used when preparing a query if the mode is set to RAG or Summary.
+  - `RAG limit`: This option is applicable only if 'Use history in RAG query' is enabled. It specifies the limit on how many recent entries in the conversation will be used when generating a query for RAG. A value of 0 indicates no limit.
+- Cache: dynamic parts of the system prompt (from plugins) have been moved to the very end of the prompt stack to enable the use of prompt cache mechanisms in OpenAI.
+
+2.4.36 (2024-11-28)
+
+- Added a new command-line argument: --workdir="/path/to/workdir" to explicitly set the current working directory.
+- Fix: start image generation in Image mode.
+
+2.4.35 (2024-11-28)
+
+- Docker removed from dependencies in Snap version #82
+- Refactored documentation.
+- Fix: toggles real-time update hook.
+- Fix: missing edit icons.
+- Added tokens from attachments to counters if mode == Full context.
+
+2.4.34 (2024-11-26)
+
+- Added a new mode: Chat with Audio, with built-in multimodal support for audio input/output. Currently in beta, the execution of commands and tools in this mode is temporarily unavailable.
+- Added new models: gpt-4o-audio-preview, gpt-4o-2024-11-20, chatgpt-4o-latest.
+- Force disabled integration with the native system menu.
+
+2.4.33 (2024-11-26)
+
+- Improved CSS and rendering of file and image lists.
+- Added displaying of used attachments in the chat window.
+
+2.4.32 (2024-11-26)
+
+- The "Add URL" option added to the "Attachments" tab allows users to include content from a given website as additional context. Currently, it only supports standard web pages and video transcription for YouTube links. More "web" options will be added in the future.
+- Added UTF-8 as default in attachments content text read/write.
+
+2.4.31 (2024-11-25)
+
+- Added an option checkbox `Auto-index on upload` in the `Attachments` tab: 
+
+Tip: To use the `RAG` mode, the file must be indexed in the vector database. This occurs automatically at the time of upload if the `Auto-index on upload` option in the `Attachments` tab is enabled. When uploading large files, such indexing might take a while - therefore, if you are using the `Full context` option, which does not use the index, you can disable the `Auto-index` option to speed up the upload of the attachment. In this case, it will only be indexed when the `RAG` option is called for the first time, and until then, attachment will be available in the form of `Full context` and `Summary`.
+
+- Added context menu options in `Uploaded attachments` tab: `Open`, `Open Source directory` and `Open Storage directory`.
+
+2.4.30 (2024-11-25)
+
+- Added instruction to model about mapped data directory in both legacy and IPython code interepreter.
+- Updated locales for plugins.
+
+2.4.29 (2024-11-25)
+
+- Added a local IPython interpreter - you can now choose between local and sandbox (Docker) in the plugin settings.
+- Added the ability to configure mapped volumes and ports for Docker containers in the plugin settings.
+- Optimized and speed-up the Llama-index plugin (inline).
+- Checkboxes replaced with Toggle buttons.
+- Improved settings dialogs.
+- Slight modification of the layout.
+- Fix: Dockerfile formatting in Code Interpreter config.
+- Fix: experts inline plugin execution.
+
+2.4.28 (2024-11-24)
+
+- Fix: issue #78
+
+2.4.27 (2024-11-24)
+
+- Profile switch fix.
+
+2.4.26 (2024-11-24)
+
+- Fix: issue #77
+
+2.4.25 (2024-11-24)
+
+- Added new plugin: System (OS), with optional sandbox support.
+- Execution of system commands moved to the System plugin.
+- Improved sandbox/Docker management.
+- Enhanced plugin settings.
+- Commands renamed to Tools, simplified layout.
+- Fix: handling of the Mouse and Keyboard plugin.
+- Fix: switching to a new context from a non-chat tab.
+- Fix: camera screenshots when the camera is not started.
+
+2.4.24 (2024-11-23)
+
+- Added the ability to use ZIP and TAR archives as attachments (they are now unpacked "on the fly").
+- Added the ability to index ZIP and TAR archives (it may be necessary to remove .zip and .tar from the blacklist in the settings).
+- Fix: error when uploading to the /data directory using the Upload files button.
+
+2.4.23 (2024-11-23)
+
+- Condensed layout widgets margins.
+- Added filename info to provided additional context from attachments.
+- Fixed auto-clear in attachments in Assistants mode.
+
+2.4.22 (2024-11-23)
+
+- Added the ability to use attachments with images, audio, and video as additional context. Tip: to enable the use of images as additional context, you need to enable the option: `Files and attachments -> Allow images as additional context`.
+- Edit icons in the chat window are enabled by default.
+
+2.4.21 (2024-11-23)
+
+- Added the ability to send additional context from attachments without needing to activate the "Chat with Files" mode. Now, you just need to attach a file, and the additional context from the file will be available in the conversation. More information can be found in the "Files and attachments" section of the documentation.
+
+2.4.20 (2024-11-22)
+
+- Fixed freeze in Windows installer. #75
+- Small fixes.
+
+2.4.19 (2024-11-22)
+
+- Added new LLM providers for Llama-index: HuggingFaceAPI and LocalAI.
+- The IPython interpreter now returns local paths to generated files and images (mapped to: %workdir%/ipython/).
+- Refactored legacy Agent and Expert modes.
+- Fixed Expert mode initialization.
+- Added an option in Settings -> Layout to disable animations.
+
+2.4.18 (2024-11-21)
+
+- Refactored kernel status and state handling.
+- Fixed: audio input execution.
+- Improved output from tools in Agents.
+- Added status loading animation indicator.
+- Other fixes.
+
+2.4.17 (2024-11-20)
+
+- Refactored kernel and render events.
+- Added multiple formatted extra outputs from plugins.
+- Added a 'Reset (clear)' option in the context list for clearing the current context.
+- Improved agents steps output handling.
+- Fixed the audio button.
+- Improved the stop event.
+- Other small fixes.
+
+2.4.16 (2024-11-19)
+
+- Code Interpreter and Files I/O input/output is now displayed in chat window, using syntax highlight.
+- Refactored plugins structure.
+- Fix: command execution in Chat in Files mode when no index is selected.
+- Fix: missing translations in Agent mode.
+
+2.4.15 (2024-11-18)
+
+- Vision analysis added to all modes.
+- Added commands for the Vision plugin: image analysis from an attachment, screenshot analysis, camera image analysis - performed in the background in every mode, without switching to vision mode.
+- Improved execution of multiple commands at once.
+- Improved integration with IPython and extended instructions for the model.
+- Other fixes and improvements.
+
+2.4.14 (2024-11-17)
+
+- Added a 'Loop / evaluate' mode for Llama-index agents, allowing them to work autonomously in a loop and evaluates the correctness of received results using a percentage scale from 0% to 100%, and automatically continue and correct responses below expected value.
+- Updated layout: mode and model lists replaced with comboboxes.
+
+2.4.13 (2024-11-16)
+
+- Introduced Code Interpreter (v2) with IPython: Enables session state retention on a kernel and building on previous computations, allowing for a Jupyter-like workflow, which is useful for iterative development and data analysis. Supports magic commands like !pip install <package_name> for package installation within the session. (currently in beta)
+
+2.4.12 (2024-11-15)
+
+- Added httpx-socks to the dependencies, enabling the use of SOCKS proxies.
+
+2.4.11 (2024-11-15)
+
+- Added a new Llama-index agent: OpenAI Assistant.
+- Added proxy settings to the configuration dialog.
+- Added more models to the Agent (Llama-index) mode.
+- Improved the agents/presets dialog window.
+- Disabled the "OpenAI API KEY is not set" Llama-index error when using a local model in Chat with Files mode. You can now use local embeddings, such as Llama3 via Ollama, and use local models without any warnings.
+
+2.4.10 (2024-11-14)
+
+- Added support for Llama Index agents. (beta)
+- Introduced a new working mode: Agent (Llama Index).
+- Added 3 Llama Index agents: OpenAI Agent, ReAct Agent, and Structured Planner Agent.
+- Fixed: passing an embed model to vector stores on indexing.
+- Fixed: python3-tk error in snap version.
+
+2.4.9 (2024-11-12)
+
+- Mouse movement has been moved to the PyAutoGUI library for seamless operation.
+- Bridge calls have been moved to an asynchronous thread.
+- Fixed the DALL-E call in Image mode.
+- Speed improvements and optimizations.
+
+2.4.8 (2024-11-12)
+
+- Fix: restoring order of notepads.
+- Fix: mouse move offset in Mouse and Keyboard plugin.
+
+2.4.7 (2024-11-11)
+
+- Added a new tool: HTML/JS Canvas, connected to the Code Interpreter plugin. This feature enables real-time rendering of HTML/JS code in a Chromium-based output by using two new Code Interpreter commands: render_html_output and get_html_output.
+- Added an SVG icon to the New Tab button.
+- Improved the system prompt and execution flow in the Mouse And Keyboard plugin and introduced a new option Auto-focus to the plugin settings (default: False).
+
+2.4.6 (2024-11-10)
+
+- Fixed notepad tab titles in Copy To menu.
+
+2.4.5 (2024-11-09)
+
+- Added a new [+] tab button to the right of the tabs.
+- Fixed the issue where the tab name disappeared when creating a new tab.
+- Fixed the broken find option (CTRL+F) in the chat window.
+
+2.4.4 (2024-11-09)
+
+- Added a new plugin: Mouse And Keyboard. The plugin allows the model to control the mouse and keyboard, control the cursor position, click mouse buttons, use scroll, type text, and press keys on the keyboard.
+
+2.4.3 (2024-11-08)
+
+- Added button to hide output from tools/plugins.
+- Added tooltips on the preset list showing the system prompt of the preset.
+- Added restoration of tooltips for chat tabs.
+- Removed disruptive tooltips from the plugin settings window.
+- Improved reading of current tab information in event reading with speech synthesis.
+- Minor improvements.
+
+2.4.2 (2024-11-08)
+
+- Improved commands and tools handling.
+- Improved autonomous mode.
+
+2.4.1 (2024-11-08)
+
+- Added titles for conversations in tabs.
+- Tab tools added to the tools menu.
+- Fix: Reload tabs after changing profile.
+- Other fixes.
+
+2.4.0 (2024-11-06)
+
+- Added the ability to have conversations in multiple tabs (right-click on the tab bar to add new tabs via "Add a new chat", similar to a web browser).
+- Added the option to add notepad tabs using the right-click context menu and selecting "Add a new notepad".
+- Added tab reorganization via drag and drop (you can now arrange tabs freely using the mouse).
+- Added the ability to name tabs.
+
+2.3.4 (2024-11-03)
+
+- Support for LaTeX: Mathematical formulas can now be displayed in the chat window using KaTeX library (https://katex.org/). This enhancement allows for real-time rendering of complex mathematical expressions.
+
+2.3.3 (2024-11-03)
+
+- Added support for models: OpenAI o1 and o1-mini and SpeakLeash/bielik-11b-v2.2 (Polish LLM: https://bielik.ai).
+
+2.3.2 (2024-08-29)
+
+- Date count fix in SQL query.
+
+2.3.1 (2024-08-29)
+
+- Fixed timezone detection and date conversions in calendar and context search.
+- Added icon indicators showing labels in context items in the calendar (to show if any day has a context with the selected label).
+- Added custom prompt templates in the input context menu (for saving, editing, and deleting custom prompts).
+
+2.3.0 (2024-08-28)
+
+- Refactored and optimized the chat engine.
+- Refactored and optimized command execution.
+- Fixed: execution of assistant tool calls.
+- Fixed: flow in the expert plugin.
+- Fixed: flow in the agent plugin.
+- Fixed: console errors in highlight.js.
+- Fixed: logging of the context used in the "Chat with Files" plugin.
+- Improved the stop command.
+- Added a reply stack.
+- Other minor fixes.
+
+2.2.33 (2024-08-28)
+
+- Improved model compatibility across different modes.
+- Enhanced appending of Llama-index response metadata (sources) to context.
+- Added scrolling to the selected item when choosing the current context from the File -> Select current menu.
+- Hidden clear preset button.
+- Fixed duplicated UUIDs in expert presets.
+- Extended context and events debugging.
+- Added non-GPT models to Agent and Expert modes.
+
+2.2.32 (2024-08-27)
+
+- Fixed the selection of the chosen index for use in Agent mode if the internal mode for Agent is Llama-index.
+- Added the ability to select an index for use by experts.
+- Added automatic, in background mode switching if the given mode is not supported by the selected model in Agent mode and for experts (this allows the use of models available only through Llama-index or Langchain in modes such as Agent or Experts).
+
+2.2.31 (2024-08-27)
+
+- Improved behavior of agent and expert calls.
+- Improved chat window auto scroll.
+- Added a new option "Always continue..." to Agent mode (as opposed to the Auto-stop option).
+- Added a new prompt: Config -> Settings -> Prompts -> Agent: continue (always, more steps).
+
+2.2.30 (2024-08-25)
+
+- Added link to Discord server in About -> Discord.
+
+2.2.29 (2024-08-25)
+
+- Fix: Removed 'Index not prepared' monit when index not created yet.
+
+2.2.28 (2024-08-25)
+
+- Fix: Added mechanism to prevent the current index from being deselected when saving settings.
+- Added models: llama3.1:70b, llama3.1:405b, and mistral-large.
+- Added configuration option: Indexes (llama-index) -> Chat -> Chat mode.
+- Split prompt templates context menu into alphabetical submenus.
+
+2.2.27 (2024-08-22)
+
+- Added functionality to hide the date suffix if date period separators are enabled.
+- Added a new option: Context -> Show date separators in pinned items on the context list, default: False.
+
+2.2.26 (2024-08-22)
+
+- Added separators for date intervals in the context list.
+- Added a new option: Context -> Show context groups on top of the context list, default: False.
+- Added a new option: Context -> Show date separators on the context list, default: True.
+- Added a new option: Context -> Show date separators in groups on the context list, default: True.
+
+2.2.25 (2024-08-22)
+
+- Improved native API functions handling.
+- Improved expert prompts.
+- Fixed/improved inline plugin commands handling.
+
+2.2.24 (2024-08-21)
+
+- Added a STOP button that allows stopping indexing at any time.
+- Improved conversion of ENUM types when generating a native list of functions for the API.
+- Disabled adding functions to the list when the option to execute commands is unchecked.
+
+2.2.23 (2024-08-21)
+
+- Improved context summarization in Llama-index provider.
+
+2.2.22 (2024-08-20)
+
+- Added new API models for "Chat with Files": Google Gemini and Anthropic Claude (see the new section in the documentation: Managing models -> "Using other models (non-GPT)" for more information on how to set API keys)
+- Added new local models for "Chat with Files": Llama 3.1, Mistral, Codellama, and Llama2-Uncensored (requires Ollama installed on the local machine - see the new section in the documentation: Managing models -> "Using other models (non-GPT)" for more information on how to enable local model support).
+- Added ability for context summarization using Llama-index models (local models can be used to summarize context titles now).
+- Added a new option in Config -> Indexes (llama-index) -> Indexing: "Stop indexing when error occurs". If enabled, indexing will stop whenever an error occurs.
+
+2.2.21 (2024-08-20)
+
+- Added inline execution for external function calls.
+- Added a stop to file indexing if an error occurs.
+
+2.2.20 (2024-08-20)
+
+- Llama-index upgraded to 0.10.65
+- Langchain upgraded to 0.2.14
+- OpenAI API upgraded to 1.41.0
+- Code syntax highlight changed from Pygments to highlight.js (better performance)
+- Added new model: gpt-4o-mini
+- Added native API function calls by default
+- Added functions importer (from plugins) into assistants
+- Fixed: input message disappear on command response in stream mode
+- Fixed: assistants tool outputs submitting
+
+2.2.19 (2024-05-16)
+
+- Added a newest multimodal model: GPT-4 "omni": https://openai.com/index/hello-gpt-4o
+
+2.2.18 (2024-05-05)
+
+- Fix: prevent crash if no audio to play.
+
+2.2.17 (2024-05-05)
+
+- Fix: Added prevent try to play audio if empty output.
+- Disabled playing finish event on audio or voice control enabled.
+
+2.2.16 (2024-05-05)
+
+- Escape key now stops response generation and audio output (if playing).
+- Voice control options added to the Audio menu.
+- Added cache on disk for generated static audio content.
+- Added plugin translations for other languages.
+
+2.2.15 (2024-05-04)
+
+- Added audio output stop on audio input start.
+- Added notify about unrecognized command.
+- Voice control improvements.
+
+2.2.14 (2024-05-04)
+
+- Added a 'Voice Control (inline)' plugin that allows for voice command control directly during a conversation.
+- Added configuration in 'Settings -> Accessibility' for a blacklist of actions available as voice commands.
+
+2.2.13 (2024-05-03)
+
+- Added stretch to dictionary config fields.
+- Removed redundant attachments clear event.
+
+2.2.12 (2024-05-03)
+
+- Improved speech recognition.
+- Added minimum required length of audio input.
+- Added missing translations.
+- Fixed settings hooks triggering on profile switch.
+
+2.2.11 (2024-05-03)
+
+- Added a blacklist for events for the voice event description in settings.
+- Added a delay to playing audio when describing events.
+- Sorted the list of events in the configuration.
+
+2.2.10 (2024-05-03)
+
+- Extended voice control commands list.
+- Extended actions and keyboard shortcuts.
+
+2.2.9 (2024-05-02)
+
+- Added more commands to voice control: search for contexts, clear search, add, read and clear calendar memos, context rename.
+
+2.2.8 (2024-05-02)
+
+- Added support for disabled people, including voice control and screen event translation with audio synthesis.
+- A new section in Settings called 'Accessibility' has been added with options for assistance: voice control, keyboard shortcut definitions for actions, and screen event translation using audio synthesis.
+- A new section called 'Accessibility' has been added to the Documentation.
+
+2.2.7 (2024-05-01)
+
+- A new experimental work mode has been added: 'Experts', which allows the creation of separate background instances with their own instructions that can be consulted for help. See the documentation: 'Work Modes / Experts'.
+- Added a new plugin: 'Experts (inline)`.
+- Improved the Agent mode by adding the ability to configure and invoke defined Experts.
+- Improved the prompts that control the autonomous mode.
+- The main prompt controlling the agents has been moved from presets to the application's settings window.
+
+2.2.6 (2024-04-30)
+
+- Added a new model: 'gpt-4-turbo'.
+- Vision integrated into Chat mode, without any plugins, if the model supports Vision - currently available for: 'gpt-4-turbo' and 'gpt-4-turbo-2024-04-09'.
+- Store importer connected with Logger.
+- Fixed: issue with batch unassigning remote files from vector stores.
+
+2.2.5 (2024-04-30)
+
+- Fix: import button handler in Assistants.
+- Refactored and improved stores batch actions events handling.
+- Added missing translations.
+
+2.2.4 (2024-04-29)
+
+- Batch actions splitted into 'Current store' and 'All stores' in Assistants remote vector stores importer.
+- Added sync current/all context menu options to Sync button.
+- Improved remote stores handling.
+
+2.2.3 (2024-04-29)
+
+- Fixed Assistants files sync btn.
+- Added batch upload files or directory in Assistants vector stores dialog.
+
+2.2.2 (2024-04-29)
+
+- Added 'Application environment' option to Config -> General for setting up custom env vars on app load.
+- Added chunk render/parse throttling to prevent high CPU load on huge text chunks.
+- Optimized and improved Code interpreter output rendering in stream mode in Assistants.
+- Improved run stopping in Assistants.
+- Fixed syntax theme and 'Edit' icon restore on profile switch.
+
+2.2.1 (2024-04-28)
+
+- Improved data reload on profile switch.
+
+2.2.0 (2024-04-28)
+
+- Improved code interpreter stream handling in Assistant mode.
+- Improved preset plugins reloading on profile switch.
+- Fixes and core improvements.
+- Updated docs to v2.2.0.
+
+2.1.83 (2024-04-27)
+
+- Index list in 'Chat with files' mode moved to combo-box at bottom.
+- Enabled display of remote images in chat output.
+- Updated docs.
+
+2.1.82 (2024-04-27)
+
+- Fixed correct store id saving if hidden thread stores on list.
+
+2.1.81 (2024-04-27)
+
+- Improved remote vector stores management.
+
+2.1.80 (2024-04-27)
+
+- Fixed missing selection in Assistant store select combo.
+- Fixed store deletion.
+- Added tooltip to Stores button.
+
+2.1.79 (2024-04-26)
+
+- OpenAI API upgraded to version 1.23.6.
+- Assistants API: added tool: File search and removed deprecated tool: Retrieval.
+- Support for remote Assistant Vector Stores added (accessible through the Assistants API).
+- Remote Vector Stores management tool introduced (right-click on an Assistant, select 'Edit', then click the database icon to open Remote Vector Stores editor).
+- Importer for Remote Assistant Vector Stores and files included.
+- Files uploaded in Assistants mode can now be shared between threads using Vector Stores.
+
+2.1.78 (2024-04-25)
+
+- Removed redundant names in block view.
+- Scrollbars background integrated with blocks bg.
+
+2.1.77 (2024-04-25)
+
+- Added the "tree" command to the I/O Files plugin to retrieve the full directory tree.
+
+2.1.76 (2024-04-25)
+
+- Chat items now displayed in blocks.
+
+2.1.75 (2024-04-24)
+
+- Copy to clipboard in web view fixed and moved to JS bridge.
+
+2.1.74 (2024-04-24)
+
+- Added syntax highlight choose to Theme menu.
+- Syntax highlight style colors integrated with Dark/Light app themes.
+
+2.1.73 (2024-04-24)
+
+- Fixed issue #50 - missing type key in config.
+
+2.1.72 (2024-04-24)
+
+- Fixed context initialization in web view on app load.
+- Improved and optimized items rendering.
+- Refactored web view CSS.
+- Rendering optimization.
+- Added real-time items reload and append.
+- Added theme CSS to scrollbars.
+- Added JS console debug to Logger window.
+
+2.1.71 (2024-04-23)
+
+- Added 160+ prompt templates from "Awesome ChatGPT Prompts" repository - to use them, right-click on the input or system prompt textarea and select the "Paste from template..." option.
+
+2.1.70 (2024-04-22)
+
+- Added web view CSS reload on theme switch.
+- Fixed time display CSS in web view.
+
+2.1.69 (2024-04-22)
+
+- Added html buffer to speed-up context initialization in web view.
+- Fixed items append in web view in agent mode.
+
+2.1.68 (2024-04-22)
+
+- Fix: CPU usage on multiple items.
+
+2.1.67 (2024-04-22)
+
+- Optimized items rendering.
+
+2.1.66 (2024-04-22)
+
+- Improved content formatting in HTML export.
+
+2.1.65 (2024-04-22)
+
+- Improved save as in Web View output.
+- Added save as text and save as html separated options.
+
+2.1.64 (2024-04-22)
+
+- Improved real-time CSS reloading.
+
+2.1.63 (2024-04-22)
+
+- Improved rendering output.
+- Updated CSS.
+
+2.1.62 (2024-04-22)
+
+- Added default lexer for code syntax highlighting if no language provided.
+
+2.1.61 (2024-04-21)
+
+- Added real-time HTML formatting of text chunks in stream mode.
+
+2.1.60 (2024-04-21)
+
+- Fixed "Save as" option in WebEngine view.
+- Added hiding of empty groups on search.
+- Updated formatting and CSS.
+
+2.1.59 (2024-04-20)
+
+- Added output renderer: WebEngine/Chromium – with full HTML/CSS/JS support. (Experimental)
+- Added a new option to choose a render engine in Settings -> General -> Rendering engine to select between WebEngine / Chromium mode and the Legacy mode (old, with simple markdown CSS support only - for compatibility reasons and troubleshooting).
+- Added syntax highlighting to code blocks – issue #43.
+- Added a new option in Settings -> Layout -> Code syntax highlight to select a highlight theme.
+- Added a new option in Settings -> Context -> Convert lists to paragraphs to enable/disable converting ul and li into p for better copying.
+- Copy to clipboard and regenerate response icons are now visible by default.
+
+2.1.58 (2024-04-19)
+
+- Fixed Markdown rendering if the content starts with a code block.
+- Added a "Switch to created profile" option in the profile creation/duplication dialogs.
+- Updated the locale.
+- Added a donate option.
+
+2.1.57 (2024-04-17)
+
+- Fixed new ctx create on empty profile if previously group was selected.
+
+2.1.56 (2024-04-17)
+
+- Added a new menu option: Clear history + groups.
+- Improved profile switching.
+
+2.1.55 (2024-04-17)
+
+- Improved result handling from Indexer tool.
+
+2.1.54 (2024-04-17)
+
+- Added data loaders reload and loaders config reload in real time on profile switch.
+
+2.1.53 (2024-04-17)
+
+- Added a new tool: Indexer, for manually indexing files, contexts, and web content, as well as managing indexes. (beta)
+
+2.1.52 (2024-04-15)
+
+- Added real-time output from code interpreter in Assistants mode.
+- Added new option in Settings > Context: Show code interpreter output.
+
+2.1.51 (2024-04-14)
+
+- Added RMB context menu to the New... context button.
+- Added filesize info to attachments and uploaded files lists.
+- Improved Assistants API stream handling.
+
+2.1.50 (2024-04-14)
+
+- Fixed selection update after group rename.
+- Added img resolution and filesize info in image preview dialog title.
+- Added filesize info in text editor dialog title.
+
+2.1.49 (2024-04-14)
+
+- Improved context group handling.
+
+2.1.48 (2024-04-14)
+
+- OpenAI API upgraded to version 1.17.1.
+- Added a stream mode to the Assistant mode (beta).
+- Fixed an issue where context group ID were not copied when duplicating context.
+
+2.1.47 (2024-04-12)
+
+- Added auto-creating new context in current group if the group is active.
+- Added sending input also with Ctrl+Enter in Shift+Enter mode.
+- Extended light style markdown CSS.
+
+2.1.46 (2024-04-12)
+
+- Improved code blocks formatting.
+- Improved attachment copy/paste.
+
+2.1.45 (2024-04-11)
+
+- Added the ability to paste images as attachments using Ctrl+V in chat input and to copy-paste images in the draw/painter.
+- Added a "Copy to Clipboard" option in code blocks.
+- Introduced a new model: gpt-4-turbo-2024-04-09.
+
+2.1.44 (2024-04-11)
+
+- Optimized "Find" option.
+- Added copy database and copy data dir checkbox options in profile duplicate dialog.
+- Added ability to reset current active profile.
+- Added missing translations.
+
+2.1.43 (2024-04-11)
+
+- The "Find" option has been extended and added to all text fields.
+- Fixed menu reload issue when switching profiles.
+- Other small fixes and improvements.
+
+2.1.42 (2024-04-10)
+
+- Improved profile switching.
+- Added interpreter internal files to excluded when indexing.
+
+2.1.41 (2024-04-10)
+
+- Added support for multiple profiles (separated config, settings and workdir), menu: Config -> Profile...
+- Added context groups for context items organizing, menu: File -> New context group...
+- Added ability to change the model on response edit and regenerate.
+- Added real-time updating number of notepads.
+- UI/theme fixes.
+
+2.1.40-post1 (2024-04-08)
+
+- Llama-index core downgraded to 0.10.13 due to issue #41
+
+2.1.40 (2024-04-08)
+
+- Added "Find" option - text search and highlighting of the found phrase in the chat and notepad window, available via CTRL + F or right-click menu / Find... (beta)
+- Added GitHub's Monaspace font family: Argon, Krypton, Neon, Radon, Xenon (reset CSS to defaults or manual replacement in CSS files is required for older versions of application to take effect).
+- Added an "Restore Default CSS" option in the "Config / Edit CSS" menu.
+- Added the ability to use custom .ttf and .otf fonts (just place them in %workdir%/fonts directory).
+
+2.1.39 (2024-03-26)
+
+- Added "Change working directory..." option in "Config" menu.
+- Improved handling reply from multiple commands at once.
+- Tools have been moved to separate parts of the app.
+- Added the ability to create custom Tools, with an example tool in the "examples" directory.
+
+2.1.38 (2024-03-20)
+
+- Added new Tools menu, with: Media player, Transcribe audio/video files, Image viewer, Text editor and Code interpreter.
+- Improved tools.
+
+2.1.38 (2024-03-20)
+
+- Added a new menu Tools with: Media player, Transcribe audio/video files, Image viewer, Text editor and Code interpreter.
+
 2.1.37 (2024-03-19)
 
 - Added generation of audio transcriptions from audio/video files.
@@ -228,7 +1029,7 @@
 2.0.171 (2024-02-27)
 
 - Added core for loading web resources (not only webpages) to Llama-index.
-- Added a data loader for transcriptions of YouTube videos (simply ask for index a YouTube video URL using the "Command: Web Search" plugin - the "web_index" command must be enabled).
+- Added a data loader for transcriptions of YouTube videos (simply ask for index a YouTube video URL using the "Web Search" plugin - the "web_index" command must be enabled).
 - Fixed the "Initial token count exceeds token limit" error in Chat with files mode.
 - Added missing translations for dictionary items in settings dialogs.
 
@@ -265,7 +1066,7 @@
 - Added search provider: Bing.
 - Added audio output providers: Google and Eleven Labs.
 - Added audio input providers: Google, Google Cloud, and Bing.
-- Added a new plugin: "Command: API calls" which allows defining commands for API calls to external services.
+- Added a new plugin: "API calls" which allows defining commands for API calls to external services.
 - Added an "Excluded file extensions" configuration option in Settings -> Llama-index.
 - Fixed audio input listener initialization in the Audio Input plugin.
 
@@ -403,11 +1204,11 @@
 
 2.0.144 (2024-02-02)
 
-- Improved Command: Context history plugin prompts
+- Improved Context history plugin prompts
 
 2.0.143 (2024-02-02)
 
-- Added a new plugin: Command: Context history (calendar)
+- Added a new plugin: Context history (calendar)
 - Added a new feature to context list: Pin on top
 - Added Minimize to tray on exit option
 
@@ -570,8 +1371,8 @@
 
 2.0.117 (2024-01-24)
 
-- Added a new feature to the "Command: Files I/O" plugin - "Get and upload file as attachment". It lets automatically read files from "data" folder and send them as attachments - just ask to send a file as an attachment and the model will send it to itself (like sending an image for analysis). Option is disabled by default in the plugin"s settings.
-- Added a new plugin: "Command: Serial port / USB". This plugin lets you read and send any commands to USB ports (so you can control robots now ;) ).
+- Added a new feature to the "Files I/O" plugin - "Get and upload file as attachment". It lets automatically read files from "data" folder and send them as attachments - just ask to send a file as an attachment and the model will send it to itself (like sending an image for analysis). Option is disabled by default in the plugin"s settings.
+- Added a new plugin: "Serial port / USB". This plugin lets you read and send any commands to USB ports (so you can control robots now ;) ).
 - Made it possible to use URLs for images when not using the vision feature.
 - Fixed saving and reloading prompts in Assistant mode.
 - Removed display of empty external images from the output.
@@ -825,7 +1626,7 @@
 
 2.0.77 (2024-01-05)
 
-- Fixed inline plugins disable when pausing command plugins by unchecking 'Execute commands' checkbox
+- Fixed inline plugins disable when pausing command plugins by unchecking '+ Tools' checkbox
 - Added real-time image appending into chat window when generating images in Image Generation mode
 - Added automatic creation of context after deletion from the list when no other context is selected
 - Updated docs
@@ -1239,8 +2040,8 @@
 
 2.0.9 (2023-12-09)
 
-- Added Command: Custom Commands feature; plugin allows to easily create and execute custom commands
-- Added new features to Command: Files I/O: downloading files, copying files and dirs, moving files and dirs
+- Added Custom Commands feature; plugin allows to easily create and execute custom commands
+- Added new features to Files I/O: downloading files, copying files and dirs, moving files and dirs
 
 2.0.8 (2023-12-08)