pygpt-net 2.7.4__py3-none-any.whl → 2.7.6__py3-none-any.whl

{pygpt_net-2.7.4.dist-info → pygpt_net-2.7.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pygpt-net
-Version: 2.7.4
+Version: 2.7.6
 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, MCP, internet access, file handling, command execution and more.
 License: MIT
 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
@@ -91,6 +91,7 @@ Requires-Dist: pandas (==2.2.3)
 Requires-Dist: paramiko (>=4.0.0,<5.0.0)
 Requires-Dist: pillow (==10.4.0)
 Requires-Dist: pinecone (>=7.0.1,<8.0.0)
+Requires-Dist: playwright (>=1.57.0,<2.0.0)
 Requires-Dist: psutil (>=7.0.0,<8.0.0)
 Requires-Dist: pydub (>=0.25.1,<0.26.0)
 Requires-Dist: pygame (>=2.6.1,<3.0.0)
@@ -119,7 +120,7 @@ Description-Content-Type: text/markdown
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.7.4** | build: **2025-12-31** | Python: **>=3.10, <3.14**
+Release: **2.7.6** | build: **2026-01-03** | Python: **>=3.10, <3.14**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -1030,6 +1031,17 @@ You can change the environment in which the navigation mode operates by using th
 - Windows
 - Mac
 
+You can run this mode in Sandbox (using `Playwright` - https://playwright.dev/) - to do it, just enable the `Sandbox` switch in the toolbox. Playwright browsers must be installed on your system. To do so, run:
+
+```bash
+pip install playwright
+playwright install <chromium|firefox|webkit>
+```
+After that, set the path to directory with installed browsers in `Mouse and Keyborad` plugin settings option: `Sandbox  (Playwright) / Browsers directory`.
+
+Compiled binary and Snap versions have `chromium` preinstalled in the package.
+
+
 **Tip:** DO NOT enable the `Mouse and Keyboard` plugin in Computer use mode—it is already connected to Computer use mode "in the background."
 
 
@@ -1198,12 +1210,14 @@ PyGPT has a preconfigured list of models (as of 2025-12-25):
 - `codex-mini` (OpenAI)
 - `dall-e-2` (OpenAI)
 - `dall-e-3` (OpenAI)
+- `deep-research-pro-preview-12-2025` (Google)
 - `deepseek-chat` (DeepSeek)
 - `deepseek-r1:1.5b` (Ollama)
 - `deepseek-r1:14b` (Ollama)
 - `deepseek-r1:32b` (Ollama)
 - `deepseek-r1:7b` (Ollama)
 - `deepseek-reasoner` (DeepSeek)
+- `gemini-2.5-computer-use-preview-10-2025` (Google)
 - `gemini-1.5-flash` (Google)
 - `gemini-1.5-pro` (Google)
 - `gemini-2.0-flash-exp` (Google)
@@ -2126,6 +2140,8 @@ PyGPT features several useful tools, including:
 - Image viewer
 - Text editor
 - Transcribe audio/video files
+- OpenAI Vector Stores
+- Google Vector Stores
 - Python Code Interpreter
 - HTML/JS Canvas (built-in HTML renderer)
 - Translator
@@ -2189,6 +2205,12 @@ A simple text editor that enables you to edit text files directly within the app
 An audio transcription tool with which you can prepare a transcript from a video or audio file. It will use a speech recognition plugin to generate the text from the file.
 
 
+## OpenAI / Google Vector Stores
+
+
+Remote vector stores management.
+
+
 ## Python Code Interpreter
 
 
@@ -3774,6 +3796,21 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.7.6 (2026-01-03)**
+
+- Fixed compatibility with xAI SDK and resolved empty responses from Grok models.
+- Fixed missing libraries in the Snap package.
+- Added zoom and grab functionality in the Image Viewer.
+- Added a zoom menu to textarea and web widgets.
+- Added the ability to close tabs with a middle mouse button click.
+
+**2.7.5 (2026-01-03)**
+
+- Added Sandbox/Playwright option to Computer Use mode.
+- Added support for Google models in Computer Use mode and introduced a new model: gemini-2.5-computer-use-preview-10-2025.
+- Added support for Google models in Research mode and introduced a new model: deep-research-pro-preview-12-2025.
+- Added the Google Vector Stores tool.
+
 **2.7.4 (2025-12-31)**
 
 - Added a splash screen.
@@ -3899,3 +3936,5 @@ Markdown parsing powered by: https://github.com/markdown-it/markdown-it
 
 LaTeX support by: https://katex.org
 
+Playwright: https://playwright.dev/
+