pygpt-net 2.4.49__py3-none-any.whl → 2.4.51__py3-none-any.whl

pygpt_net/plugin/audio_input/simple.py

@@ -6,16 +6,15 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.08 00:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
-import pyaudio
-import wave
 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
 
 
@@ -32,9 +31,6 @@ class Simple:
         """
         self.plugin = plugin
         self.is_recording = False
-        self.frames = []
-        self.p = None
-        self.stream = None
         self.timer = None
 
     def toggle_recording(self):
@@ -59,56 +55,48 @@ class Simple:
         """Stop timeout"""
         self.stop_recording(timeout=True)
 
-    def start_recording(self):
-        """Start recording"""
-        self.frames = []  # clear audio frames
+    def start_recording(self, force: bool = False):
+        """
+        Start recording
 
-        def callback(in_data, frame_count, time_info, status):
-            self.frames.append(in_data)
-            if self.is_recording:
-                return (in_data, pyaudio.paContinue)
-            else:
-                return (in_data, pyaudio.paComplete)
+        :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:
-            self.is_recording = True
-            self.switch_btn_stop()
-
             # stop audio output if playing
             if self.plugin.window.controller.audio.is_playing():
                 self.plugin.window.controller.audio.stop_output()
 
+            # set audio volume bar
+            self.plugin.window.core.audio.capture.set_bar(
+                self.plugin.window.ui.plugin_addon['audio.input.btn'].bar
+            )
+
             # start timeout timer to prevent infinite recording
             if self.timer is None:
                 self.timer = QTimer()
                 self.timer.timeout.connect(self.stop_timeout)
                 self.timer.start(self.TIMEOUT_SECONDS * 1000)
 
-            # select audio input device
-            device_id = int(self.plugin.window.core.config.get('audio.input.device', 0))
-            rate = int(self.plugin.window.core.config.get('audio.input.rate', 44100))
-            channels = int(self.plugin.window.core.config.get('audio.input.channels', 1))
-            if not self.plugin.window.core.audio.is_device_compatible(device_id):
-                err = self.plugin.window.core.audio.get_last_error()
-                message = "Selected audio input device is not compatible. Please select another one. ERROR: " + str(err)
-                self.is_recording = False
-                self.plugin.window.core.debug.log(message)
-                self.plugin.window.ui.dialogs.alert(message)
-                self.switch_btn_start()  # switch button to start
-                return
-
-            self.p = pyaudio.PyAudio()
-            self.stream = self.p.open(format=pyaudio.paInt16,
-                                      channels=channels,
-                                      rate=rate,
-                                      input=True,
-                                      input_device_index=device_id,
-                                      frames_per_buffer=1024,
-                                      stream_callback=callback)
+            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()
+            self.plugin.window.core.audio.capture.start()  # start recording if audio is OK
             self.plugin.window.update_status(trans('audio.speak.now'))
             self.plugin.window.dispatch(AppEvent(AppEvent.INPUT_VOICE_LISTEN_STARTED))  # app event
-            self.stream.start_stream()
         except Exception as e:
             self.is_recording = False
             self.plugin.window.core.debug.log(e)
@@ -127,6 +115,7 @@ class Simple:
 
         :param timeout: True if stopped due to timeout
         """
+        self.plugin.window.core.audio.capture.reset_audio_level()
         self.is_recording = False
         self.plugin.window.dispatch(AppEvent(AppEvent.INPUT_VOICE_LISTEN_STOPPED))  # app event
         if self.timer:
@@ -134,30 +123,31 @@ class Simple:
             self.timer = None
         self.switch_btn_start()  # switch button to start
         path = os.path.join(self.plugin.window.core.config.path, self.plugin.input_file)
+        self.plugin.window.core.audio.capture.set_path(path)
 
-        if self.stream is not None:
-            self.stream.stop_stream()
-            self.stream.close()
-            self.p.terminate()
-
+        if self.plugin.window.core.audio.capture.has_source():
+            self.plugin.window.core.audio.capture.stop()  # stop recording
             # abort if timeout
             if timeout:
                 self.plugin.window.update_status("Aborted.".format(self.TIMEOUT_SECONDS))
                 return
 
-            if self.frames:
-                if len(self.frames) < self.MIN_FRAMES:
+            if self.plugin.window.core.audio.capture.has_frames():
+                frames = self.plugin.window.core.audio.capture.get_frames()
+                if len(frames) < self.MIN_FRAMES:
                     self.plugin.window.update_status(trans("status.audio.too_short"))
                     self.plugin.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STOPPED))  # app event
                     return
-                wf = wave.open(path, 'wb')
-                channels = int(self.plugin.window.core.config.get('audio.input.channels', 1))
-                rate = int(self.plugin.window.core.config.get('audio.input.rate', 44100))
-                wf.setnchannels(channels)
-                wf.setsampwidth(self.p.get_sample_size(pyaudio.paInt16))
-                wf.setframerate(rate)
-                wf.writeframes(b''.join(self.frames))
-                wf.close()
+
                 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/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/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

@@ -6,14 +6,17 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.20 21:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
 from PySide6.QtCore import Qt
-from PySide6.QtWidgets import QLabel, QHBoxLayout, QWidget, QPushButton
+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):
@@ -25,20 +28,24 @@ 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)
         self.btn_toggle.setMinimumWidth(200)
 
+        self.bar = LevelBar(self)
+        self.bar.setLevel(0)
+
         # status
         self.status = QLabel("")
         self.status.setStyleSheet("color: #999; font-size: 10px; font-weight: 400; margin: 0; padding: 0; border: 0;")
         self.status.setMaximumHeight(15)
 
-        self.layout = QHBoxLayout(self)
+        self.layout = QVBoxLayout(self)
         self.layout.addWidget(self.btn_toggle)
-        self.layout.addWidget(self.status)
+        # self.layout.addWidget(self.status)
+        self.layout.addWidget(self.bar)
 
         # self.layout.addWidget(self.stop)
         self.layout.setAlignment(Qt.AlignCenter)
@@ -76,25 +83,43 @@ 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)
         self.btn_toggle.setMinimumWidth(200)
 
-        # status
-        self.status = QLabel("")
-        self.status.setStyleSheet("color: #999; font-size: 10px; font-weight: 400; margin: 0; padding: 0; border: 0;")
-        self.status.setMaximumHeight(15)
+        self.bar = LevelBar(self)
+        self.bar.setLevel(0)
 
-        self.layout = QHBoxLayout(self)
-        self.layout.addWidget(self.btn_toggle)
-        self.layout.addWidget(self.status)
+        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.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):
         """
@@ -104,15 +129,50 @@ 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)
         self.window.dispatch(event)
+
+
+class LevelBar(QWidget):
+    def __init__(self, parent=None):
+        super().__init__(parent)
+        self._level = 0.0  # level from 0.0 to 100.0
+        self.setFixedSize(200, 5)  # bar size
+
+    def setLevel(self, level):
+        """
+        Set volume level
+
+        :param level: level
+        """
+        self._level = level
+        self.update()
+
+    def paintEvent(self, event):
+        """
+        Paint event
+
+        :param event: event
+        """
+        painter = QPainter(self)
+        painter.fillRect(self.rect(), Qt.transparent)
+        level_width = (self._level / 100.0) * self.width()
+        painter.setBrush(Qt.green)
+        painter.setPen(Qt.NoPen)
+        painter.drawRect(0, 0, level_width, self.height())
+
+    """
+        # --- bar from center ---
+        def paintEvent(self, event):
+        painter = QPainter(self)
+        painter.fillRect(self.rect(), Qt.transparent)
+        level_width = (self._level / 100.0) * self.width()
+        half_level_width = level_width / 2
+        center_x = self.width() / 2
+        rect_x = center_x - half_level_width
+        painter.setBrush(Qt.green)
+        painter.setPen(Qt.NoPen)
+        painter.drawRect(rect_x, 0, level_width, self.height())
+    """

pygpt_net/ui/widget/dialog/snap.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.02.26 22:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 from PySide6.QtWidgets import QDialog, QLabel, QVBoxLayout, QPushButton
@@ -55,7 +55,7 @@ class SnapDialogAudioInput(QDialog):
         self.window = window
         self.setParent(window)
         self.setWindowTitle("Snap is detected")
-        self.cmd = CmdLabel(self.window, "sudo snap connect pygpt:audio-record :audio-record")
+        self.cmd = CmdLabel(self.window, "sudo snap connect pygpt:alsa && sudo snap connect pygpt:audio-record :audio-record")
 
         self.btn = QPushButton("OK")
         self.btn.clicked.connect(self.accept)

pygpt_net/ui/widget/dialog/update.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.02.17 20:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 import os
@@ -177,7 +177,8 @@ class UpdateDialog(BaseDialog):
                 if self.window.core.platforms.is_windows():
                     self.download_link = download_windows
                     self.download_file.setText("{} .msi ({})".format(trans("action.download"), version))
-                    self.download_file.setVisible(True)
+                    self.download_file.setVisible(False)  # Windows Store: disabled
+                    self.info_upgrade.setVisible(False)  # Windows Store: disabled
                 elif self.window.core.platforms.is_linux():
                     self.download_link = download_linux
                     self.download_file.setText("{} .tar.gz ({})".format(trans("action.download"), version))

{pygpt_net-2.4.49.dist-info → pygpt_net-2.4.51.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pygpt-net
-Version: 2.4.49
+Version: 2.4.51
 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: **2.4.49** | build: **2025.01.16** | Python: **>=3.10, <3.13**
+Release: **2.4.51** | build: **2025.01.17** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -209,6 +209,7 @@ sudo snap connect pygpt:camera
 
 ```commandline
 sudo snap connect pygpt:audio-record :audio-record
+sudo snap connect pygpt:alsa
 ```
 
 **Connecting IPython in Docker in Snap version**:
@@ -4043,6 +4044,16 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**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.
+- Added audio input volume progress bar.
+
 **2.4.49 (2025-01-16)**
 
 - Fix: stream render in Assistants mode.
@@ -4068,67 +4079,6 @@ 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>