pygpt-net 2.4.50__py3-none-any.whl → 2.4.52__py3-none-any.whl

pygpt_net/data/locale/locale.zh.ini

@@ -136,6 +136,7 @@ audio.control.btn = 语音控制
 audio.magic_word.detected = 檢測到魔法詞！
 audio.magic_word.invalid= 不是魔法詞 :(
 audio.magic_word.please= 請說出魔法詞...
+audio.speak.btn.continuous = 连续录音
 audio.speak.btn.stop = 停止
 audio.speak.btn.stop.tooltip = 點擊停止麥克風聆聽
 audio.speak.btn.tooltip = 點擊開始麥克風聆聽
@@ -875,6 +876,8 @@ settings.audio.input.device = 音频输入设备
 settings.audio.input.device.desc = 选择用于麦克风输入的音频设备。
 settings.audio.input.rate = 采样率
 settings.audio.input.rate.desc = 采样率，默认: 44100
+settings.audio.input.stop_interval = 连续录音自动转录间隔
+settings.audio.input.stop_interval.desc = 自动转录音频片段的间隔（以秒为单位），默认：10
 settings.check_updates = 啟動時檢查更新
 settings.check_updates.bg = 在後台檢查更新
 settings.cmd.field.desc = 启用 `{cmd}` 工具。

pygpt_net/plugin/audio_input/simple.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.16 17:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
 import os
@@ -14,6 +14,7 @@ import os
 from PySide6.QtCore import QTimer
 
 from pygpt_net.core.events import AppEvent
+from pygpt_net.core.tabs.tab import Tab
 from pygpt_net.utils import trans
 
 
@@ -54,8 +55,20 @@ class Simple:
         """Stop timeout"""
         self.stop_recording(timeout=True)
 
-    def start_recording(self):
-        """Start recording"""
+    def start_recording(self, force: bool = False):
+        """
+        Start recording
+
+        :param force: True to force recording
+        """
+        # enable continuous mode if notepad tab is active
+        self.plugin.window.core.audio.capture.stop_callback = self.on_stop
+        continuous_enabled = self.plugin.window.core.config.get('audio.input.continuous', False)
+        if continuous_enabled and self.plugin.window.controller.ui.tabs.get_current_type() == Tab.TAB_NOTEPAD:
+            self.plugin.window.core.audio.capture.loop = True  # set loop
+        else:
+            self.plugin.window.core.audio.capture.loop = False
+
         try:
             # stop audio output if playing
             if self.plugin.window.controller.audio.is_playing():
@@ -72,11 +85,12 @@ class Simple:
                 self.timer.timeout.connect(self.stop_timeout)
                 self.timer.start(self.TIMEOUT_SECONDS * 1000)
 
-            if not self.plugin.window.core.audio.capture.check_audio_input():
-                raise Exception("Audio input not working.")
-                # IMPORTANT!!!!
-                # Stop here if audio input not working!
-                # This prevents the app from freezing when audio input is not working!
+            if not force:
+                if not self.plugin.window.core.audio.capture.check_audio_input():
+                    raise Exception("Audio input not working.")
+                    # IMPORTANT!!!!
+                    # Stop here if audio input not working!
+                    # This prevents the app from freezing when audio input is not working!
 
             self.is_recording = True
             self.switch_btn_stop()
@@ -128,3 +142,12 @@ class Simple:
                 self.plugin.handle_thread(True)  # handle transcription in simple mode
         else:
             self.plugin.window.update_status("")
+
+
+    def on_stop(self):
+        """Handle auto-transcribe"""
+        path = os.path.join(self.plugin.window.core.config.path, self.plugin.input_file)
+        self.plugin.window.core.audio.capture.set_path(path)
+        self.plugin.window.core.audio.capture.stop()
+        self.plugin.window.core.audio.capture.start()
+        self.plugin.handle_thread(True)

pygpt_net/plugin/cmd_files/worker.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.18 21:00:00                  #
+# Updated Date: 2025.01.17 13:00:00                  #
 # ================================================== #
 
 import fnmatch
@@ -160,6 +160,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"] or "data" not in item["params"]:
+                return self.make_response(item, "Path or data not provided")
             path = self.prepare_path(item["params"]['path'])
             data = item["params"]['data']
             self.msg = "Saving file: {}".format(path)
@@ -180,6 +182,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"] or "data" not in item["params"]:
+                return self.make_response(item, "Path or data not provided")
             path = self.prepare_path(item["params"]['path'])
             data = item["params"]['data']
             self.msg = "Appending file: {}".format(path)
@@ -201,6 +205,8 @@ class Worker(BaseWorker):
         """
         context_result = ""
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             self.msg = "Reading file: {}".format(item["params"]['path'])
             self.log(self.msg)
             path = item["params"]['path']
@@ -232,6 +238,8 @@ class Worker(BaseWorker):
         context = None
         query = None
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Reading path: {}".format(path)
             self.log(self.msg)
@@ -283,6 +291,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Deleting file: {}".format(path)
             self.log(self.msg)
@@ -372,6 +382,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Creating directory: {}".format(path)
             self.log(self.msg)
@@ -394,6 +406,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Deleting directory: {}".format(path)
             self.log(self.msg)
@@ -416,6 +430,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "src" not in item["params"] or "dst" not in item["params"]:
+                return self.make_response(item, "Source or destination not provided")
             dst = self.prepare_path(item["params"]['dst'])
             self.msg = "Downloading file: {} into {}".format(item["params"]['src'], dst)
             self.log(self.msg)
@@ -468,6 +484,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "src" not in item["params"] or "dst" not in item["params"]:
+                return self.make_response(item, "Source or destination not provided")
             src = self.prepare_path(item["params"]['src'])
             dst = self.prepare_path(item["params"]['dst'])
             self.msg = "Copying file: {} into {}".format(src, dst)
@@ -487,6 +505,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "src" not in item["params"] or "dst" not in item["params"]:
+                return self.make_response(item, "Source or destination not provided")
             src = self.prepare_path(item["params"]['src'])
             dst = self.prepare_path(item["params"]['dst'])
             self.msg = "Copying directory: {} into {}".format(src, dst)
@@ -506,6 +526,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "src" not in item["params"] or "dst" not in item["params"]:
+                return self.make_response(item, "Source or destination not provided")
             src = self.prepare_path(item["params"]['src'])
             dst = self.prepare_path(item["params"]['dst'])
             self.msg = "Moving: {} into {}".format(src, dst)
@@ -525,6 +547,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Checking if directory exists: {}".format(path)
             self.log(self.msg)
@@ -546,6 +570,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Checking if file exists: {}".format(path)
             self.log(self.msg)
@@ -567,6 +593,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Checking if path exists: {}".format(path)
             self.log(self.msg)
@@ -588,6 +616,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Checking file size: {}".format(path)
             self.log(self.msg)
@@ -613,6 +643,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Checking file info: {}".format(path)
             self.log(self.msg)
@@ -666,6 +698,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "path" not in item["params"]:
+                return self.make_response(item, "Path not provided")
             path = self.prepare_path(item["params"]['path'])
             self.msg = "Adding attachment: {}".format(path)
             self.log(self.msg)
@@ -728,6 +762,8 @@ class Worker(BaseWorker):
         :return: response item
         """
         try:
+            if "pattern" not in item["params"]:
+                return self.make_response(item, "Search pattern not provided")
             recursive = True
             path = self.plugin.window.core.config.get_user_dir('data')
             pattern = item["params"]['pattern']

pygpt_net/provider/core/config/patch.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.16 20:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
 import copy
@@ -1803,6 +1803,14 @@ class Patch:
                     data["api_key_hugging_face"] = ""
                 updated = True
 
+            # < 2.4.51
+            if old < parse_version("2.4.51"):
+                print("Migrating config from < 2.4.51...")
+                if 'audio.input.stop_interval' not in data:
+                    data["audio.input.stop_interval"] = 10
+                if 'audio.input.continuous' not in data:
+                    data["audio.input.continuous"] = False
+
         # update file
         migrated = False
         if updated:

pygpt_net/ui/__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: 2025.01.17 13:00:00                  #
 # ================================================== #
 
 import os
@@ -109,9 +109,10 @@ class UI:
     def set_initial_size(self):
         """Set default sizes"""
         def set_initial_splitter_height():
+            """Set initial splitter height"""
             total_height = self.window.ui.splitters['main.output'].size().height()
             if total_height > 0:
-                size_output = int(total_height * 0.8)
+                size_output = int(total_height * 0.9)
                 size_input = total_height - size_output
                 self.window.ui.splitters['main.output'].setSizes([size_output, size_input])
             else:
@@ -119,6 +120,7 @@ class UI:
         QTimer.singleShot(0, set_initial_splitter_height)
 
         def set_initial_splitter_width():
+            """Set initial splitter width"""
             total_width = self.window.ui.splitters['main'].size().width()
             if total_width > 0:
                 size_output = int(total_width * 0.7)

pygpt_net/ui/layout/chat/input.py

@@ -160,24 +160,12 @@ class Input:
 
         grid = QGridLayout()
 
-        #left_layout = QHBoxLayout()
-        #left_layout.addWidget(self.window.ui.nodes['input.label'])
-        #left_layout.addWidget(self.window.ui.nodes['inline.vision'])
-        #left_layout.addStretch(1)
-
         center_layout = QHBoxLayout()
         center_layout.addStretch()
         center_layout.addWidget(self.window.ui.plugin_addon['audio.input'])
         center_layout.addWidget(self.window.ui.plugin_addon['audio.input.btn'])
         center_layout.addStretch()
-
-        #right_layout = QHBoxLayout()
-        #right_layout.addStretch(1)
-        #right_layout.addWidget(self.window.ui.nodes['input.counter'])
-
-        #grid.addLayout(left_layout, 0, 0)
         grid.addLayout(center_layout, 0, 1, alignment=Qt.AlignCenter)
-        #grid.addLayout(right_layout, 0, 2, alignment=Qt.AlignRight)
 
         grid.setContentsMargins(0, 0, 0, 0)
         return grid

pygpt_net/ui/menu/__init__.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.16 01:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
 from .about import About
@@ -50,15 +50,16 @@ class Menu:
         self.audio.setup()
         self.video.setup()
         self.config.setup()
-        self.about.setup()
 
     def post_setup(self):
         """Post setup menus"""
         # tools menu
         self.tools.setup()
-        self.donate.setup()
+        self.about.setup()
 
         # debug menu
         show = self.window.core.config.get('debug')
         self.debug.setup()
         self.window.ui.menu['menu.debug'].menuAction().setVisible(show)
+
+        self.donate.setup()

pygpt_net/ui/widget/audio/input_button.py

@@ -6,15 +6,17 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.16 17:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
 from PySide6.QtCore import Qt
-from PySide6.QtGui import QPainter
+from PySide6.QtGui import QPainter, QIcon
 from PySide6.QtWidgets import QLabel, QHBoxLayout, QWidget, QPushButton, QVBoxLayout
 
 from pygpt_net.core.events import Event, AppEvent
+from pygpt_net.ui.widget.option.toggle_label import ToggleLabel
 from pygpt_net.utils import trans
+import pygpt_net.icons_rc
 
 class VoiceControlButton(QWidget):
     def __init__(self, window=None):
@@ -26,7 +28,7 @@ class VoiceControlButton(QWidget):
         super(VoiceControlButton, self).__init__(window)
         self.window = window
 
-        self.btn_toggle = QPushButton(trans('audio.control.btn'))
+        self.btn_toggle = QPushButton(QIcon(":/icons/mic.svg"), trans('audio.control.btn'))
         self.btn_toggle.clicked.connect(self.toggle_recording)
         self.btn_toggle.setToolTip(trans('audio.speak.btn.tooltip'))
         self.btn_toggle.setCursor(Qt.PointingHandCursor)
@@ -81,7 +83,7 @@ class AudioInputButton(QWidget):
         super(AudioInputButton, self).__init__(window)
         self.window = window
 
-        self.btn_toggle = QPushButton(trans('audio.speak.btn'))
+        self.btn_toggle = QPushButton(QIcon(":/icons/mic.svg"), trans('audio.speak.btn'))
         self.btn_toggle.clicked.connect(self.toggle_recording)
         self.btn_toggle.setToolTip(trans('audio.speak.btn.tooltip'))
         self.btn_toggle.setCursor(Qt.PointingHandCursor)
@@ -90,20 +92,34 @@ class AudioInputButton(QWidget):
         self.bar = LevelBar(self)
         self.bar.setLevel(0)
 
-        # status
-        #self.status = QLabel("xxx")
-        #self.status.setStyleSheet("color: #999; font-size: 10px; font-weight: 400; margin: 0; padding: 0; border: 0;")
-        #self.status.setMaximumHeight(15)
+        btn_layout = QVBoxLayout()
+        btn_layout.addWidget(self.btn_toggle)
+        btn_layout.addWidget(self.bar)
+        btn_layout.setContentsMargins(0, 0, 0, 0)
+        btn_widget = QWidget()
+        btn_widget.setLayout(btn_layout)
 
-        self.layout = QVBoxLayout(self)
-        self.layout.addWidget(self.btn_toggle)
-        #self.layout.addWidget(self.status)
-        self.layout.addWidget(self.bar)
+        self.continuous = ToggleLabel(trans('audio.speak.btn.continuous'), label_position="right")
+        self.continuous.box.stateChanged.connect(
+            lambda: self.window.controller.audio.toggle_continuous(
+                self.continuous.box.isChecked())
+        )
+
+        self.notepad_layout = QHBoxLayout()
+        self.notepad_layout.addWidget(self.continuous)
+        self.notepad_layout.setContentsMargins(0, 0, 0, 0)
+
+        self.notepad_footer = QWidget()
+        self.notepad_footer.setLayout(self.notepad_layout)
+
+        self.layout = QHBoxLayout()
+        self.layout.addWidget(btn_widget)
+        self.layout.addWidget(self.notepad_footer)
+        self.layout.setContentsMargins(0, 0, 0, 0)
 
-        # self.layout.addWidget(self.stop)
-        self.layout.setAlignment(Qt.AlignCenter)
         self.setLayout(self.layout)
-        self.setMaximumHeight(80)
+        btn_widget.setMaximumHeight(80)
+        self.setMaximumHeight(120)
 
     def add_widget(self, widget):
         """
@@ -113,14 +129,6 @@ class AudioInputButton(QWidget):
         """
         self.layout.addWidget(widget)
 
-    def set_status(self, text):
-        """
-        Set status text
-
-        :param text: text
-        """
-        self.status.setText(text)
-
     def toggle_recording(self):
         """Toggle recording"""
         event = Event(Event.AUDIO_INPUT_RECORD_TOGGLE)

{pygpt_net-2.4.50.dist-info → pygpt_net-2.4.52.dist-info}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2024 Marcin Szczygliński
+Copyright (c) 2025 Marcin Szczygliński
 
 GitHub: https://github.com/szczyglis-dev/py-gpt
 

{pygpt_net-2.4.50.dist-info → pygpt_net-2.4.52.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pygpt-net
-Version: 2.4.50
+Version: 2.4.52
 Summary: Desktop AI Assistant powered by models: OpenAI o1, GPT-4o, GPT-4, GPT-4 Vision, GPT-3.5, DALL-E 3, Llama 3, Mistral, Gemini, Claude, Bielik, and other models supported by Langchain, Llama Index, and Ollama. Features include chatbot, text completion, image generation, vision analysis, speech-to-text, internet access, file handling, command execution and more.
 Home-page: https://pygpt.net
 License: MIT
@@ -93,7 +93,7 @@ Description-Content-Type: text/markdown
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.4.50** | build: **2025.01.16** | Python: **>=3.10, <3.13**
+Release: **2.4.52** | build: **2025.01.17** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -4044,6 +4044,17 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.4.52 (2025-01-17)**
+
+- Improved audio input button visibility toggle.
+- Fix: check for required arguments - issue #88.
+- UI Fixes.
+
+**2.4.51 (2025-01-17)**
+
+- Added a "Continuous recording" mode under Audio Input in the Notepad tab, allowing for recording long voice notes and real-time auto-transcription. (beta)
+- A new option has been added in Settings -> Audio -> Continuous recording auto-transcribe interval.
+
 **2.4.50 (2025-01-16)**
 
 - Refactored audio input core.
@@ -4074,67 +4085,6 @@ may consume additional tokens that are not displayed in the main window.
 - 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.
-
-
 # Credits and links
 
 **Official website:** <https://pygpt.net>