pygpt-net 2.6.21__py3-none-any.whl → 2.6.23__py3-none-any.whl

{pygpt_net-2.6.21.dist-info → pygpt_net-2.6.23.dist-info}/METADATA

@@ -1,9 +1,9 @@
 Metadata-Version: 2.3
 Name: pygpt-net
-Version: 2.6.21
-Summary: Desktop AI Assistant powered by: OpenAI GPT-5, o1, o3, GPT-4, Gemini, Claude, Grok, DeepSeek, and other models supported by Llama Index, and Ollama. Chatbot, agents, completion, image generation, vision analysis, speech-to-text, plugins, internet access, file handling, command execution and more.
+Version: 2.6.23
+Summary: Desktop AI Assistant powered by: OpenAI GPT-5, GPT-4, o1, o3, Gemini, Claude, Grok, DeepSeek, and other models supported by Llama Index, and Ollama. Chatbot, agents, completion, image generation, vision analysis, speech-to-text, plugins, internet access, file handling, command execution and more.
 License: MIT
-Keywords: py_gpt,py-gpt,pygpt,desktop,app,o1,o3,gpt-5,gpt,gpt4,gpt-4o,gpt-4v,gpt3.5,gpt-4,gpt-4-vision,gpt-3.5,llama3,mistral,gemini,grok,deepseek,bielik,claude,tts,whisper,vision,chatgpt,dall-e,chat,chatbot,assistant,text completion,image generation,ai,api,openai,api key,langchain,llama-index,ollama,presets,ui,qt,pyside
+Keywords: ai,api,api key,app,assistant,bielik,chat,chatbot,chatgpt,claude,dall-e,deepseek,desktop,gemini,gpt,gpt-3.5,gpt-4,gpt-4-vision,gpt-4o,gpt-5,gpt-oss,gpt3.5,gpt4,grok,langchain,llama-index,llama3,mistral,o1,o3,ollama,openai,presets,py-gpt,py_gpt,pygpt,pyside,qt,text completion,tts,ui,vision,whisper
 Author: Marcin Szczyglinski
 Author-email: info@pygpt.net
 Requires-Python: >=3.10,<3.14
@@ -111,7 +111,7 @@ Description-Content-Type: text/markdown
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.6.21** | build: **2025-08-24** | Python: **>=3.10, <3.14**
+Release: **2.6.23** | build: **2025-08-25** | Python: **>=3.10, <3.14**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -123,15 +123,15 @@ Release: **2.6.21** | build: **2025-08-24** | Python: **>=3.10, <3.14**
 
 ## Overview
 
-**PyGPT** is **all-in-one** Desktop AI Assistant that provides direct interaction with OpenAI language models, including `gpt-5`, `o1`, `o3`, `gpt-4o`, `gpt-4`, `gpt-4 Vision`, and `gpt-3.5`, through the `OpenAI API`. By utilizing `LlamaIndex`, the application also supports alternative LLMs, like those available on `HuggingFace`, locally available models via `Ollama` (like `Llama 3`,`Mistral`, `DeepSeek V3/R1` or `Bielik`), `Google Gemini`, `Anthropic Claude`, `Perplexity Sonar`, and `xAI Grok`.
+**PyGPT** is **all-in-one** Desktop AI Assistant that provides direct interaction with OpenAI language models, including `GPT-5`, `GPT-4`, `o1`, `o3` and more, through the `OpenAI API`. By utilizing `LlamaIndex`, the application also supports alternative LLMs, like those available on `HuggingFace`, locally available models via `Ollama` (like `gpt-oss`, `Llama 3`,`Mistral`, `DeepSeek V3/R1` or `Bielik`), and other models like `Google Gemini`, `Anthropic Claude`, `Perplexity / Sonar`, and `xAI Grok`.
 
-This assistant offers multiple modes of operation such as chat, assistants, completions, and image-related tasks using `DALL-E 3` for generation and `gpt-4 Vision` for image analysis. **PyGPT** has filesystem capabilities for file I/O, can generate and run Python code, execute system commands, execute custom commands and manage file transfers. It also allows models to perform web searches with the `Google` and `Microsoft Bing`.
+This assistant offers multiple modes of operation such as chat, assistants, agents, completions, and image-related tasks like image generation and image analysis. **PyGPT** has filesystem capabilities for file I/O, can generate and run Python code, execute system commands, execute custom commands and manage file transfers. It also allows models to perform web searches with the `Google` and `Microsoft Bing`.
 
 For audio interactions, **PyGPT** includes speech synthesis using the `Microsoft Azure`, `Google`, `Eleven Labs` and `OpenAI` Text-To-Speech services. Additionally, it features speech recognition capabilities provided by `OpenAI Whisper`, `Google` and `Bing` enabling the application to understand spoken commands and transcribe audio inputs into text. It features context memory with save and load functionality, enabling users to resume interactions from predefined points in the conversation. Prompt creation and management are streamlined through an intuitive preset system.
 
-**PyGPT**'s functionality extends through plugin support, allowing for custom enhancements. Its multi-modal capabilities make it an adaptable tool for a range of AI-assisted operations, such as text-based interactions, system automation, daily assisting, vision applications, natural language processing, code generation and image creation.
+**PyGPT**'s functionality extends through plugin support, allowing for custom enhancements (with multiple plugins included). Its multi-modal capabilities make it an adaptable tool for a range of AI-assisted operations, such as text-based interactions, system automation, daily assisting, vision applications, natural language processing, code generation and image creation.
 
-Multiple operation modes are included, such as chat, text completion, assistant, vision, Chat with Files (via `LlamaIndex`), commands execution, external API calls and image generation, making **PyGPT** a multi-tool for many AI-driven tasks.
+Multiple operation modes are included, such as chat, text completion, assistant, agents, vision, Chat with Files (via `LlamaIndex`), commands execution, external API calls and image generation, making **PyGPT** a multi-tool for many AI-driven tasks.
 
 **Showcase** (mp4, version `2.5.65`, build `2025-07-24`):
 
@@ -152,7 +152,7 @@ You can download compiled 64-bit versions for Windows and Linux here: https://py
 - Desktop AI Assistant for `Linux`, `Windows` and `Mac`, written in Python.
 - Works similarly to `ChatGPT`, but locally (on a desktop computer).
 - 12 modes of operation: Chat, Chat with Files, Chat with Audio, Research (Perplexity), Completion, Image generation, Vision, Assistants, Experts, Computer use, Agents and Autonomous Mode.
-- Supports multiple models: `gpt-5`, `o1`, `o3`, `GPT-4o`, `GPT-4`, `GPT-3.5`, and any model accessible through `LlamaIndex` and `Ollama` such as `Llama 3`, `Mistral`, `Google Gemini`, `Anthropic Claude`, `xAI Grok`, `DeepSeek V3/R1`, `Perplexity Sonar`, `Bielik`, etc.
+- Supports multiple models like `OpenAI GPT-5`, `GPT-4`, `o1`, `o3`, `o4`, `Google Gemini`, `Anthropic Claude`, `xAI Grok`, `DeepSeek V3/R1`, `Perplexity / Sonar`, and any model accessible through `LlamaIndex` and `Ollama` such as `DeepSeek`, `gpt-oss`, `Llama 3`, `Mistral`, `Bielik`, etc.
 - Chat with your own Files: integrated `LlamaIndex` support: chat with data such as: `txt`, `pdf`, `csv`, `html`, `md`, `docx`, `json`, `epub`, `xlsx`, `xml`, webpages, `Google`, `GitHub`, video/audio, images and other data types, or use conversation history as additional context provided to the model.
 - Built-in vector databases support and automated files and data embedding.
 - Included support features for individuals with disabilities: customizable keyboard shortcuts, voice control, and translation of on-screen actions into audio via speech synthesis.
@@ -161,7 +161,7 @@ You can download compiled 64-bit versions for Windows and Linux here: https://py
 - Speech synthesis via `Microsoft Azure`, `Google`, `Eleven Labs` and `OpenAI` Text-To-Speech services.
 - Speech recognition via `OpenAI Whisper`, `Google` and `Microsoft Speech Recognition`.
 - Real-time video camera capture in Vision mode.
-- Image analysis via `GPT-4 Vision` and `GPT-4o`.
+- Image analysis via `GPT-5` and `GPT-4o`.
 - Integrated calendar, day notes and search in contexts by selected date.
 - Tools and commands execution (via plugins: access to the local filesystem, Python Code Interpreter, system commands execution, and more).
 - Custom commands creation and execution.
@@ -179,7 +179,7 @@ You can download compiled 64-bit versions for Windows and Linux here: https://py
 - Fully configurable.
 - Themes support.
 - Real-time code syntax highlighting.
-- Plugins support.
+- Plugins support with built-in plugins like `Files I/O`, `Code Interpreter`, `Web Search`, `Google`, `Facebook`, `X/Twitter`, `Slack`, `Telegram`, `GitHub`, and many more.
 - Built-in token usage calculation.
 - Possesses the potential to support future OpenAI models.
 - **Open source**; source code is available on `GitHub`.
@@ -278,7 +278,7 @@ pygpt
 
 ## Running from GitHub source code
 
-An alternative method is to download the source code from `GitHub` and execute the application using the Python interpreter (`>=3.10`, `<3.13`). 
+An alternative method is to download the source code from `GitHub` and execute the application using the Python interpreter (`>=3.10`, `<3.14`). 
 
 ### Install with pip
 
@@ -1915,7 +1915,7 @@ PyGPT can be extended with:
 
 - custom plugins
 
-- custom LLMs wrappers
+- custom LLMs
 
 - custom vector store providers
 
@@ -1927,14 +1927,16 @@ PyGPT can be extended with:
 
 - custom web search engine providers
 
+- custom agents
+
 
 See the section `Extending PyGPT / Adding a custom plugin` for more details.
 
-# Functions and commands execution
+# Functions, commands and tools
 
 **Tip** remember to enable the `+ Tools` checkbox to enable execution of tools and commands from plugins.
 
-From version `2.2.20` PyGPT uses native API function calls by default. You can go back to internal syntax (described below) by switching off option `Config -> Settings -> Prompts -> Use native API function calls`. Native API function calls are available in Chat, Completion and Assistant modes only (using OpenAI API).
+From version `2.2.20` PyGPT uses native API function calls by default. You can go back to internal syntax (described below) by switching off option `Config -> Settings -> Prompts -> Use native API function calls`. You must also enable `Tool calls` checkbox in model advanced settings to use native function calls with the specified model.
 
 In background, **PyGPT** uses an internal syntax to define commands and their parameters, which can then be used by the model and executed on the application side or even directly in the system. This syntax looks as follows (example command below):
 
@@ -1942,33 +1944,28 @@ In background, **PyGPT** uses an internal syntax to define commands and their pa
 
 It is a JSON object wrapped between `<tool>` tags. The application extracts the JSON object from such formatted text and executes the appropriate function based on the provided parameters and command name. Many of these types of commands are defined in plugins (e.g., those used for file operations or internet searches). You can also define your own commands using the `Custom Commands` plugin, or simply by creating your own plugin and adding it to the application.
 
-**Tip:** The `+ Tools` option checkbox must be enabled to allow the execution of commands from plugins. Disable the option if you do not want to use commands, to prevent additional token usage (as the command execution system prompt consumes additional tokens).
+**Tip:** The `+ Tools` option checkbox must be enabled to allow the execution of commands from plugins. Disable the option if you do not want to use commands, to prevent additional token usage (as the command execution system prompt consumes additional tokens and may slow down local models).
 
 ![v2_code_execute](https://github.com/szczyglis-dev/py-gpt/raw/master/docs/source/images/v2_code_execute.png)
 
 When native API function calls are disabled, a special system prompt responsible for invoking commands is added to the main system prompt if the `+ Tools` option is active.
 
 However, there is an additional possibility to define your own commands and execute them with the help of model.
-These are functions - defined on the OpenAI API side and described using JSON objects. You can find a complete guide on how to define functions here:
+These are functions / tools - defined on the API side and described using JSON objects. You can find a complete guide on how to define functions here:
 
 https://platform.openai.com/docs/guides/function-calling
 
 https://cookbook.openai.com/examples/how_to_call_functions_with_chat_models
 
-PyGPT offers compatibility of these functions with commands used in the application. All you need to do is define the appropriate functions using the syntax required by OpenAI, and PyGPT will do the rest, translating such syntax on the fly into its own internal format.
-
-You can define functions for modes: `Chat` and `Assistants`.
-Note that - in Chat mode, they should be defined in `Presets`, and for Assistants, in the `Assistant` settings.
+PyGPT offers compatibility of these functions with commands (tools) used in the application. All you need to do is define the appropriate functions using the correct JSON schema, and PyGPT will do the rest, translating such syntax on the fly into its own internal format.
 
-**Example of usage:**
+Local functions and tools from plugins are available in all modes, except `Assistants`.
 
-1) Chat
-
-Create a new Preset, open the Preset edit dialog and add a new function using `+ Function` button with the following content:
+To enable local functions for `Assistants` mode (in this mode remote tools are used by default), create a new Assistant, open the Preset edit dialog and import tools from plugins or add a new function using `+ Function` button e.g. with the following content:
 
 **Name:** `send_email`
 
-**Description:** `Sends a quote using email`
+**Description:** `Send a quote using email`
 
 **Params (JSON):**
 
@@ -1991,7 +1988,7 @@ Then, in the `Custom Commands` plugin, create a new command with the same name a
 
 **Command name:** `send_email`
 
-**Instruction/prompt:** `send mail` *(don't needed, because it will be called on OpenAI side)*
+**Instruction/prompt:** `send mail`
 
 **Params list:** `quote`
 
@@ -1999,7 +1996,7 @@ Then, in the `Custom Commands` plugin, create a new command with the same name a
 
 At next, enable the `+ Tools` option and enable the plugin.
 
-Ask model in Chat mode:
+Ask a model:
 
 ```Create a funny quote and email it```
 
@@ -2013,12 +2010,7 @@ As a result, response like this will be sent to the model:
 
 ```[{"request": {"cmd": "send_email"}, "result": "OK. Email sent: Why do we tell actors to 'break a leg?' Because every play has a cast!"}]```
 
-
-2) Assistant
-
-In this mode (via Assistants API), it should be done similarly, with the difference that here the functions should be defined in the assistant's settings.
-
-With this flow you can use both forms - OpenAI and PyGPT - to define and execute commands and functions in the application. They will cooperate with each other and you can use them interchangeably.
+With this flow you can use both forms - API provider JSON schema and PyGPT schema - to define and execute commands and functions in the application. They will cooperate with each other and you can use them interchangeably.
 
 # Tools
 
@@ -3536,6 +3528,18 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.6.23 (2025-08-25)**
+
+- Added an inline "Add a new chat" button to the right of the tabs.
+- Added an "Add Attachment" button in the input field.
+- Improved file open in the system's file manager
+- Fixed the restoration of input text color when changing themes from light to dark.
+- Fixed last eval step finish if 100% complete.
+- 
+**2.6.22 (2025-08-25)**
+
+- UI refactor and optimizations.
+
 **2.6.21 (2025-08-24)**
 
 - Ollama models are now available in OpenAI Agents mode.
@@ -3550,146 +3554,6 @@ may consume additional tokens that are not displayed in the main window.
 - Added a new plugin: Server (FTP/SSH) - connect to remote servers using FTP, SFTP, and SSH. Execute remote commands, upload, download, and more (beta).
 - Added support for Wayland in Snap/compiled versions.
 
-**2.6.19 (2025-08-22)**
-
-- Fixed: added prevention for summarizing an empty context.
-- Improved the speed of context item refreshing.
-
-**2.6.18 (2025-08-21)**
-
-- Refactor and optimizations.
-- Fix: Evolve agent stop event calling.
-
-**2.6.17 (2025-08-21)**
-
-- Optimized profile switching.
-- Fixed: setting initial splitter size on first launch.
-- Added smoother view reload.
-
-**2.6.16 (2025-08-20)**
-
-- Fixed: Attachment string joining.
-- Improved expert function calls.
-- Added sorting to the plugin list.
-
-**2.6.15 (2025-08-20)**
-
-- Added: do not change the context menu font size in text editing.
-- Added: do not reload context items on tab change if already loaded.
-- Fixed: appending of names and avatars in the stream chunk.
-
-**2.6.14 (2025-08-19)**
-
-- Fixed: Agent evaluation tool runs even if tools are disabled.
-- Extended agent response evaluation by providing the full context of the output.
-
-**2.6.13 (2025-08-19)**
-
-- Fix: Do not load the index in experts if it is not provided.
-- Fix: Load remote images in the webview.
-- Fix: Presets list refresh.
-- Optimize context items reload.
-
-**2.6.12 (2025-08-19)**
-
-- Optimized web renderer memory cleanup.
-
-**2.6.11 (2025-08-18)**
-
-- Added the ability to close the dialog window with the Esc key.
-- Made context item deletion without output refresh.
-- Optimizations.
-
-**2.6.10 (2025-08-17)**
-
-- Enhanced the handling of the context list.
-- Integrated RAG into OpenAI Agents.
-- Enhanced RAG management in Agents.
-- Added an option: Config -> Agents -> General -> Auto-retrieve additional context from RAG.
-- Included Google Docs, Maps, and Colab in the Google plugin.
-
-**2.6.9 (2025-08-17)**
-
-- Added two new agents for LlamaIndex and OpenAI: Supervisor and Worker (beta).
-
-**2.6.8 (2025-08-16)**
-
-- Fixed: updated paragraph color on theme switch.
-- Added switching to duplicated preset after creation.
-- Reduced delay after selecting context.
-- Optimized rendering of mathematical formulas.
-
-**2.6.7 (2025-08-16)**
-
-- Fix: missing entity sanitize.
-
-**2.6.6 (2025-08-16)**
-
-- Output rendering optimization.
-
-**2.6.5 (2025-08-16)**
-
-- Fix: crash when creating a context in a new group.
-- Fix: high CPU usage after switching profiles.
-
-**2.6.4 (2025-08-15)**
-
-- Fix: tool execution in OpenAI Agents.
-- Optimizations.
-
-**2.6.3 (2025-08-15)**
-
-- Optimized streaming and CPU usage.
-- Fixed crash on set label color and ctx duplicate.
-
-**2.6.2 (2025-08-15)**
-
-- Added plugins (beta): Google, Facebook, X/Twitter, Telegram, Slack, GitHub, Bitbucket.
-
-**2.6.1 (2025-08-14)**
-
-- LlamaIndex Agents refactored to Workflows.
-
-**2.6.0 (2025-08-13)**
-
-- Added split responses to the OpenAI Agents in non-streaming mode.
-- Disabled auto-scroll when manually scrolled to the top.
-- Increased scrollbar width in the light theme.
-- Optimized the clearing of the streaming buffer.
-- Optimized imports.
-- Made CSS improvements.
-
-**2.5.98 (2025-08-12)**
-
-- Added support for GPT-5 in LlamaIndex/Chat with Files mode.
-- Experts are now allowed in all OpenAI agent types.
-- Improved the output of OpenAI agents (separated context items).
-- Refactored memory cleanup for thread workers.
-- Optimized streaming.
-
-**2.5.97 (2025-08-11)**
-
-- Fix: attribute error in prev ctx.
-
-**2.5.96 (2025-08-10)**
-
-- Fixed memory leaks.
-
-**2.5.95 (2025-08-09)**
-
-- Added user info personalization in Config -> Personalization, where you can provide information about yourself to the model.
-- Added presets personalization with configurable AI names and avatars.
-- Added a search field in the Translator tool.
-- Fixed <> tags replacement in code blocks.
-
-**2.5.94 (2025-08-09)**
-
-- Added a new LLM provider: HuggingFace Router.
-- Introduced a new model: gpt-oss (OpenAI open-source model available in HuggingFace and Ollama).
-- Added a new agent mode in OpenAI Agents: Bot 2 Bot.
-- Fixed: Storing the last used context ID when empty.
-- Fixed: Reloading items when an agent run is stopped.
-
 # Credits and links
 
 **Official website:** <https://pygpt.net>