pygpt-net 2.4.37__py3-none-any.whl → 2.4.41__py3-none-any.whl

CHANGELOG.md

@@ -1,5 +1,34 @@
 # CHANGELOG
 
+## 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`.

README.md

@@ -2,7 +2,7 @@
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.4.37** | build: **2024.11.30** | Python: **>=3.10, <3.12**
+Release: **2.4.41** | build: **2024.12.14** | Python: **>=3.10, <3.12**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -1984,6 +1984,10 @@ Per-page content chunk size (max characters per chunk). *Default:* `20000`
 
 Disables SSL verification when crawling web pages. *Default:* `False`
 
+- `Use raw content (without summarization)` *raw*
+
+Return raw content from web search instead of summarized content. Provides more data but consumes more tokens. *Default:* `True`
+
 - `Timeout` *timeout*
 
 Connection timeout (seconds). *Default:* `5`
@@ -1994,7 +1998,7 @@ User agent to use when making requests. *Default:* `Mozilla/5.0`.
 
 - `Max result length` *max_result_length*
 
-Max length of summarized result (characters). *Default:* `1500`
+Max length of the summarized or raw result (characters). *Default:* `50000`
 
 - `Max summary tokens` *summary_max_tokens*
 
@@ -2680,6 +2684,8 @@ Config -> Settings...
 
 - `Zoom`: Adjusts the zoom in chat window (web render view). `WebEngine / Chromium` render mode only.
 
+- `Style (chat)`: Chat style (Blocks, or ChatGPT-like, or ChatGPT-like Wide. `WebEngine / Chromium` render mode only.
+
 - `Code syntax highlight`: Syntax highlight theme in code blocks. `WebEngine / Chromium` render mode only.
 
 - `Font Size (chat window)`: Adjusts the font size in the chat window (plain-text) and notepads.
@@ -2702,8 +2708,6 @@ Config -> Settings...
 
 - `Use theme colors in chat window`: Use color theme in chat window, Default: True.
 
-- `Disable markdown formatting in output`: Enables plain-text display in output window, Default: False.
-
 **Files and attachments**
 
 - `Store attachments in the workdir upload directory`: Enable to store a local copy of uploaded attachments for future use. Default: True
@@ -2814,14 +2818,22 @@ Config -> Settings...
 
 **Vision**
 
+- `Vision: Camera Input Device`: Video capture camera index (index of the camera, default: 0).
+
 - `Vision: Camera capture width (px)`: Video capture resolution (width).
 
 - `Vision: Camera capture height (px)`: Video capture resolution (height).
 
-- `Vision: Camera IDX (number)`: Video capture camera index (number of camera).
-
 - `Vision: Image capture quality`: Video capture image JPEG quality (%).
 
+**Audio**
+
+- `Audio Input Device`: Selects the audio device for Microphone input.
+
+- `Channels`: Input channels, default: 1
+
+- `Sampling Rate`: Sampling rate, default: 44100
+
 **Indexes (LlamaIndex)**
 
 - `Indexes`: List of created indexes.
@@ -3865,125 +3877,42 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
-**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)**
+**2.4.41 (2024-12-14)**
 
-- 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.
+- Improved switching between columns on a split screen.
+- Added visual identification of the active column.
 
-**2.4.31 (2024-11-25)**
+**2.4.40 (2024-12-13)**
 
-- Added an option checkbox `Auto-index on upload` in the `Attachments` tab: 
+- 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.
 
-**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`.
+**2.4.39 (2024-12-09)**
 
-- Added context menu options in `Uploaded attachments` tab: `Open`, `Open Source directory` and `Open Storage directory`.
+- 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.
 
-**2.4.30 (2024-11-25)**
+- Fixed: Language switch.
 
-- Added instruction to model about mapped data directory in both legacy and IPython code interepreter.
-- Updated locales for plugins.
+**2.4.38 (2024-12-08)**
 
-**2.4.29 (2024-11-25)**
+- 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.
 
-- 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 LlamaIndex 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.
-
-- Fixed the issue with restarting the agent after it has been forcefully stopped.
-
-**2.4.20 (2024-11-22)**
-
-- Fixed freeze in Windows installer. #75
-- Small fixes.
-
-**2.4.19 (2024-11-22)**
+**2.4.37 (2024-11-30)**
 
-- Added new LLM providers for LlamaIndex: 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.
+- 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.
 
 
 # Credits and links

pygpt_net/CHANGELOG.txt

@@ -1,3 +1,32 @@
+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`.

pygpt_net/__init__.py

@@ -6,15 +6,15 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.30 01:00:00                  #
+# Updated Date: 2024.12.14 08:00:00                  #
 # ================================================== #
 
 __author__ = "Marcin Szczygliński"
 __copyright__ = "Copyright 2024, Marcin Szczygliński"
 __credits__ = ["Marcin Szczygliński"]
 __license__ = "MIT"
-__version__ = "2.4.37"
-__build__ = "2024.11.30"
+__version__ = "2.4.41"
+__build__ = "2024.12.14"
 __maintainer__ = "Marcin Szczygliński"
 __github__ = "https://github.com/szczyglis-dev/py-gpt"
 __website__ = "https://pygpt.net"

pygpt_net/controller/__init__.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.21 17:00:00                  #
+# Updated Date: 2024.12.09 23:00:00                  #
 # ================================================== #
 
 from pygpt_net.controller.access import Access
@@ -87,15 +87,16 @@ class Controller:
         self.chat.init()
 
         # setup layout
-        self.ui.pre_setup()
         self.layout.setup()
         self.ui.setup()
+        self.ui.tabs.setup()
 
         # setup controllers
         self.lang.setup()
         self.assistant.setup()
         self.chat.setup()
         self.agent.setup()
+        self.tools.setup()
         self.ctx.setup()
         self.presets.setup()
         self.idx.setup()
@@ -105,7 +106,8 @@ class Controller:
         self.attachment.setup()
         self.camera.setup_ui()
         self.access.setup()
-        self.tools.setup()
+
+
 
     def post_setup(self):
         """Post-setup, after plugins are loaded"""
@@ -116,6 +118,7 @@ class Controller:
         self.calendar.setup()  # after everything is loaded
         self.painter.setup()  # load previous image if exists
         self.debug.post_setup()  # post setup debug after all loaded
+        self.ui.tabs.restore_data()  # restore opened tabs data
 
         # show license terms dialog
         if not self.window.core.config.get('license.accepted'):
@@ -168,6 +171,7 @@ class Controller:
         # post-reload
         self.ui.tabs.reload_after()
         self.ctx.reload_after()
+        self.ui.tabs.restore_data()  # restore opened tabs data
         self.kernel.restart()
 
         self.reloading = False  # unlock

pygpt_net/controller/access/control.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.26 19:00:00                  #
+# Updated Date: 2024.12.14 08:00:00                  #
 # ================================================== #
 
 import re

pygpt_net/controller/access/voice.py

@@ -6,9 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.20 21:00:00                  #
+# Updated Date: 2024.12.14 08:00:00                  #
 # ================================================== #
 
+from typing import Optional, List, Dict, Any
+
 import pyaudio
 import wave
 import os
@@ -59,7 +61,7 @@ class Voice:
         """Setup voice control"""
         self.update()
 
-    def delayed_play(self, text: str, event: AppEvent = None):
+    def delayed_play(self, text: str, event: AppEvent):
         """
         Delayed play audio
 
@@ -185,7 +187,11 @@ class Voice:
             self.enable_voice_control()
 
     def is_voice_control_enabled(self) -> bool:
-        """Check if voice control is enabled"""
+        """
+        Check if voice control is enabled
+
+        :return: True if enabled
+        """
         return self.window.core.config.get("access.voice_control")
 
     def toggle_recording(self):
@@ -342,7 +348,7 @@ class Voice:
         self.window.tools.get("transcriber").on_transcribe(path, text)
 
     @Slot(object, object)
-    def handle_input(self, text: str, ctx: CtxItem = None):
+    def handle_input(self, text: str, ctx: Optional[CtxItem] = None):
         """
         Insert text to input and send
 
@@ -356,7 +362,7 @@ class Voice:
         commands = self.window.core.access.voice.recognize_commands(text)
         self.handle_commands(commands)
 
-    def handle_commands(self, commands: list):
+    def handle_commands(self, commands: List[Dict[str, Any]]):
         """
         Handle commands
 

pygpt_net/controller/agent/experts.py

@@ -6,9 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.21 20:00:00                  #
+# Updated Date: 2024.12.14 08:00:00                  #
 # ================================================== #
 
+from typing import Optional, Any
+
 from pygpt_net.core.types import (
     MODE_AGENT,
     MODE_EXPERT,
@@ -44,9 +46,7 @@ class Experts:
         return self.is_stop
 
     def unlock(self):
-        """
-        Unlock experts
-        """
+        """Unlock experts"""
         self.is_stop = False
 
     def enabled(self) -> bool:
@@ -61,7 +61,12 @@ class Experts:
             return True
         return False
 
-    def append_prompts(self, mode: str, sys_prompt: str, parent_id: str = None):
+    def append_prompts(
+            self,
+            mode: str,
+            sys_prompt: str,
+            parent_id: Optional[str] = None
+    ):
         """
         Append prompt to the window
 
@@ -151,7 +156,7 @@ class Experts:
                             return num_calls  # abort continue if expert call detected
         return num_calls
 
-    def log(self, data: any):
+    def log(self, data: Any):
         """
         Log data to debug
 

pygpt_net/controller/agent/legacy.py

@@ -6,9 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.21 20:00:00                  #
+# Updated Date: 2024.12.14 08:00:00                  #
 # ================================================== #
 
+from typing import Optional, List, Dict, Any
+
 from pygpt_net.core.types import (
     MODE_AGENT,
     MODE_AGENT_LLAMA,
@@ -109,7 +111,7 @@ class Legacy:
         self.window.ui.nodes['status.agent'].setText(status)
         self.window.controller.agent.common.toggle_status()
 
-    def get_functions(self) -> list:
+    def get_functions(self) -> List[Dict[str, Any]]:
         """
         Append goal commands
 
@@ -137,7 +139,7 @@ class Legacy:
     def on_system_prompt(
             self,
             prompt: str,
-            append_prompt: str = "",
+            append_prompt: Optional[str] = "",
             auto_stop: bool = True,
     ) -> str:
         """
@@ -286,7 +288,7 @@ class Legacy:
     def on_cmd(
             self,
             ctx: CtxItem,
-            cmds: list,
+            cmds: List[Dict[str, Any]],
     ):
         """
         Event: On commands
@@ -300,7 +302,7 @@ class Legacy:
     def cmd(
             self,
             ctx: CtxItem,
-            cmds: list,
+            cmds: List[Dict[str, Any]],
     ):
         """
         Event: On command
@@ -378,7 +380,7 @@ class Legacy:
                 mode="agent",
             )
 
-    def hook_update(self, key, value, caller, *args, **kwargs):
+    def hook_update(self, key: str, value: Any, caller, *args, **kwargs):
         """
         Hook: on option update
 

pygpt_net/controller/agent/llama.py

@@ -6,9 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.21 20:00:00                  #
+# Updated Date: 2024.12.14 08:00:00                  #
 # ================================================== #
 
+from typing import Any
+
 from pygpt_net.core.events import KernelEvent
 from pygpt_net.core.bridge.context import BridgeContext
 from pygpt_net.item.ctx import CtxItem
@@ -134,7 +136,7 @@ class Llama:
         """Update agent status"""
         pass
 
-    def hook_update(self, key, value, caller, *args, **kwargs):
+    def hook_update(self, key: str, value: Any, caller, *args, **kwargs):
         """
         Hook: on option update
 

pygpt_net/controller/assistant/__init__.py

@@ -6,9 +6,10 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.20 21:00:00                  #
+# Updated Date: 2024.12.14 08:00:00                  #
 # ================================================== #
 
+from typing import Optional
 import webbrowser
 
 from pygpt_net.item.assistant import AssistantItem
@@ -22,7 +23,7 @@ from .threads import Threads
 from pygpt_net.core.text.utils import has_unclosed_code_tag
 from pygpt_net.utils import trans
 from pygpt_net.item.ctx import CtxItem
-from ...core.events import RenderEvent
+from pygpt_net.core.events import RenderEvent
 
 
 class Assistant:
@@ -49,7 +50,7 @@ class Assistant:
         """
         Update assistants list
 
-        :param update_list: update list
+        :param update_list: True if update list
         """
         if update_list:
             self.update_list()
@@ -244,7 +245,11 @@ class Assistant:
         self.window.update_status(trans('status.assistant.cleared'))
         self.update()
 
-    def delete(self, idx: int = None, force: bool = False):
+    def delete(
+            self,
+            idx: Optional[int] = None,
+            force: bool = False
+    ):
         """
         Delete assistant