pygpt-net 2.4.49__tar.gz → 2.4.50__tar.gz

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/CHANGELOG.md

@@ -1,5 +1,10 @@
 # CHANGELOG
 
+## 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.

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pygpt-net
-Version: 2.4.49
+Version: 2.4.50
 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: **2.4.50** | build: **2025.01.16** | 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 +4044,11 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**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.

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/README.md

@@ -2,7 +2,7 @@
 
 [![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: **2.4.50** | build: **2025.01.16** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -118,6 +118,7 @@ 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**:
@@ -3952,6 +3953,11 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**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.

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pygpt-net"
-version = "2.4.49"
+version = "2.4.50"
 description = "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."
 authors = ["Marcin Szczyglinski <info@pygpt.net>"]
 license = "MIT"

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/src/pygpt_net/CHANGELOG.txt

@@ -1,3 +1,8 @@
+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.

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/src/pygpt_net/__init__.py

@@ -6,14 +6,14 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.16 01:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 __author__ = "Marcin Szczygliński"
 __copyright__ = "Copyright 2025, Marcin Szczygliński"
 __credits__ = ["Marcin Szczygliński"]
 __license__ = "MIT"
-__version__ = "2.4.49"
+__version__ = "2.4.50"
 __build__ = "2025.01.16"
 __maintainer__ = "Marcin Szczygliński"
 __github__ = "https://github.com/szczyglis-dev/py-gpt"

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/src/pygpt_net/controller/access/voice.py

@@ -6,13 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 08:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 from typing import Optional, List, Dict, Any
 
-import pyaudio
-import wave
 import os
 
 from PySide6.QtCore import QTimer, Slot
@@ -38,9 +36,6 @@ class Voice:
         """
         self.window = window
         self.is_recording = False
-        self.frames = []
-        self.p = None
-        self.stream = None
         self.timer = None
         self.input_file = "voice_control.wav"
         self.thread_started = False
@@ -218,15 +213,6 @@ class Voice:
 
     def start_recording(self):
         """Start recording"""
-        self.frames = []  # clear audio frames
-
-        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)
-
         try:
             self.is_recording = True
             self.switch_btn_stop()
@@ -235,23 +221,26 @@ class Voice:
             if self.window.controller.audio.is_playing():
                 self.window.controller.audio.stop_output()
 
+            # set audio volume bar
+            self.window.core.audio.capture.set_bar(
+                self.window.ui.nodes['voice.control.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)
 
-            self.p = pyaudio.PyAudio()
-            self.stream = self.p.open(format=pyaudio.paInt16,
-                                      channels=1,
-                                      rate=44100,
-                                      input=True,
-                                      frames_per_buffer=1024,
-                                      stream_callback=callback)
+            if not self.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.window.core.audio.capture.start()  # start recording if audio is OK
             self.window.update_status(trans('audio.speak.now'))
             self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STARTED))  # app event
-            self.stream.start_stream()
         except Exception as e:
             self.is_recording = False
             self.window.core.debug.log(e)
@@ -270,35 +259,29 @@ class Voice:
 
         :param timeout: True if stopped due to timeout
         """
+        self.window.core.audio.capture.reset_audio_level()
         self.is_recording = False
         if self.timer:
             self.timer.stop()
             self.timer = None
         self.switch_btn_start()  # switch button to start
         path = os.path.join(self.window.core.config.path, self.input_file)
+        self.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.window.core.audio.capture.has_source():
+            self.window.core.audio.capture.stop()  # stop recording
             # abort if timeout
             if timeout:
                 self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STOPPED))  # app event
                 self.window.update_status("Aborted.".format(self.TIMEOUT_SECONDS))
                 return
 
-            if self.frames:
-                if len(self.frames) < self.MIN_FRAMES:
+            if self.window.core.audio.capture.has_frames():
+                frames = self.window.core.audio.capture.get_frames()
+                if len(frames) < self.MIN_FRAMES:
                     self.window.update_status(trans("status.audio.too_short"))
                     self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STOPPED))  # app event
                     return
-                wf = wave.open(path, 'wb')
-                wf.setnchannels(1)
-                wf.setsampwidth(self.p.get_sample_size(pyaudio.paInt16))
-                wf.setframerate(44100)
-                wf.writeframes(b''.join(self.frames))
-                wf.close()
                 self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_SENT))  # app event
                 self.handle_thread(True)  # handle transcription in simple mode
         else:

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/src/pygpt_net/core/audio/__init__.py

@@ -6,17 +6,19 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 18:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 import re
 from typing import Union, Optional, Tuple, List
 
+from PySide6.QtMultimedia import QMediaDevices
 from bs4 import UnicodeDammit
 
 from pygpt_net.provider.audio_input.base import BaseProvider as InputBaseProvider
 from pygpt_net.provider.audio_output.base import BaseProvider as OutputBaseProvider
 
+from .capture import Capture
 from .whisper import Whisper
 
 
@@ -28,6 +30,7 @@ class Audio:
         :param window: Window instance
         """
         self.window = window
+        self.capture = Capture(window)
         self.whisper = Whisper(window)
         self.providers = {
             "input": {},
@@ -41,21 +44,12 @@ class Audio:
 
         :return devices list: [(id, name)]
         """
-        import pyaudio
-        devices = []
-        try:
-            p = pyaudio.PyAudio()
-            num_devices = p.get_device_count()
-            for i in range(num_devices):
-                info = p.get_device_info_by_index(i)
-                if info["maxInputChannels"] > 0:
-                    dammit = UnicodeDammit(info["name"])
-                    devices.append((i, dammit.unicode_markup))
-                    # print(f"Device ID {i}: {info['name']}")
-            p.terminate()
-        except Exception as e:
-            print(f"Audio input devices receive error: {e}")
-        return devices
+        devices = QMediaDevices.audioInputs()
+        devices_list = []
+        for index, device in enumerate(devices):
+            dammit = UnicodeDammit(device.description())
+            devices_list.append((index, dammit.unicode_markup))
+        return devices_list
 
     def is_device_compatible(self, device_index: int) -> bool:
         """
@@ -69,7 +63,6 @@ class Audio:
         channels = int(self.window.core.config.get('audio.input.channels', 1))
         p = pyaudio.PyAudio()
         info = p.get_device_info_by_index(device_index)
-        supported = False
         try:
             p.is_format_supported(
                 rate=rate,

pygpt_net-2.4.50/src/pygpt_net/core/audio/capture.py

@@ -0,0 +1,331 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# ================================================== #
+# This file is a part of PYGPT package               #
+# Website: https://pygpt.net                         #
+# GitHub:  https://github.com/szczyglis-dev/py-gpt   #
+# MIT License                                        #
+# Created By  : Marcin Szczygliński                  #
+# Updated Date: 2025.01.16 17:00:00                  #
+# ================================================== #
+
+import numpy as np
+import wave
+
+from PySide6.QtMultimedia import QAudioFormat, QMediaDevices, QAudioSource
+
+class Capture:
+    def __init__(self, window=None):
+        """
+        Audio input capture core
+
+        :param window: Window instance
+        """
+        self.window = window
+        self.audio_source = None
+        self.audio_io_device = None
+        self.frames = []
+        self.actual_audio_format = None
+        self.path = None
+        self.disconnected = False
+        self.devices = []
+        self.selected_device = None
+        self.bar = None
+        self.check_audio_devices()
+
+    def set_path(self, path: str):
+        """
+        Set audio input file path
+
+        :param path: file path
+        """
+        self.path = path
+
+    def set_bar(self, bar):
+        """
+        Set audio level bar
+
+        :param bar: audio level bar
+        """
+        self.bar = bar
+
+    def check_audio_devices(self):
+        """Check audio input devices"""
+        self.devices = QMediaDevices.audioInputs()
+        if not self.devices:
+            # no devices found
+            self.selected_device = None
+            print("No audio input devices found.")
+        else:
+            # set the first device as default
+            self.selected_device = self.devices[0]
+
+    def device_changed(self, index: int):
+        """
+        Change audio input device
+
+        :param index: device index
+        """
+        if 0 <= index < len(self.devices):
+            self.selected_device = self.devices[index]
+        else:
+            self.selected_device = None
+
+    def prepare_device(self):
+        """Set the current audio input device"""
+        device_id = int(self.window.core.config.get('audio.input.device', 0))
+        self.device_changed(device_id)
+
+    def start(self):
+        """
+        Start audio input recording
+
+        :return: True if started
+        """
+        # Clear previous frames
+        self.frames = []
+
+        # Prepare selected device
+        self.prepare_device()
+        if not self.selected_device:
+            print("No audio input device selected")
+            return
+        if self.disconnected:
+            print("Audio source disconnected, please connect the audio source")
+            return False
+
+        # Prevent multiple recordings
+        if self.audio_source is not None:
+            return False
+
+        # Set up audio input and start recording
+        self.setup_audio_input()
+        return True
+
+    def stop(self):
+        """
+        Stop audio input recording
+
+        :return: True if stopped
+        """
+        result = False
+        if self.audio_source is not None:
+            # Disconnect the readyRead signal
+            self.audio_io_device.readyRead.disconnect(self.process_audio_input)
+            self.audio_source.stop()
+            self.audio_source = None
+            self.audio_io_device = None
+
+            # Save frames to file (if any)
+            if self.frames:
+                self.save_audio_file(self.path)
+                result = True
+            else:
+                print("No audio data recorded")
+        return result
+
+    def has_source(self) -> bool:
+        """
+        Check if audio source is available
+
+        :return: True if available
+        """
+        if self.audio_source is not None:
+            return True
+        return False
+
+    def has_frames(self) -> bool:
+        """
+        Check if audio frames are available
+
+        :return: True if available
+        """
+        if self.frames:
+            return True
+        return False
+
+    def get_frames(self) -> list:
+        """
+        Get recorded audio frames
+
+        :return: list of frames
+        """
+        return self.frames
+
+    def setup_audio_input(self):
+        """Set up audio input device and start recording"""
+        if not self.selected_device:
+            print("No audio input device selected")
+            return
+
+        # Define audio format
+        audio_format = QAudioFormat()
+        audio_format.setSampleRate(int(self.window.core.config.get('audio.input.rate', 44100)))
+        audio_format.setChannelCount(int(self.window.core.config.get('audio.input.channels', 1)))
+        audio_format.setSampleFormat(QAudioFormat.SampleFormat.Int16)
+
+        # Select default audio input device
+        audio_input_device = self.selected_device
+
+        # Check if the format is supported
+        if not audio_input_device.isFormatSupported(audio_format):
+            print("Requested format not supported, using nearest format.")
+            audio_format = audio_input_device.preferredFormat()
+
+        # Store the actual format being used
+        self.actual_audio_format = audio_format
+
+        # Create QAudioSource object with the device and format
+        try:
+            self.audio_source = QAudioSource(audio_input_device, audio_format)
+        except Exception as e:
+            self.disconnected = True
+            print(f"Failed to create audio source: {e}")
+
+        # Start audio input and obtain the QIODevice
+        try:
+            self.audio_io_device = self.audio_source.start()
+            if self.audio_io_device is None:
+                raise Exception("Unable to access audio input device")
+        except Exception as e:
+            print(f"Failed to start audio input: {e}")
+            self.disconnected = True
+            self.audio_source = None
+            self.audio_io_device = None
+            return
+
+        # Connect the readyRead signal to process incoming data
+        self.audio_io_device.readyRead.connect(self.process_audio_input)
+
+    def process_audio_input(self):
+        """Process incoming audio data"""
+        data = self.audio_io_device.readAll()
+        if data.isEmpty():
+            return
+
+        # Convert QByteArray to bytes
+        data_bytes = data.data()
+
+        # Append raw data to frames list for saving
+        self.frames.append(data_bytes)
+
+        # Determine the correct dtype and normalization factor
+        sample_format = self.actual_audio_format.sampleFormat()
+        dtype = self.get_dtype_from_sample_format(sample_format)
+        normalization_factor = self.get_normalization_factor(sample_format)
+
+        # Convert bytes to NumPy array of the appropriate type
+        samples = np.frombuffer(data_bytes, dtype=dtype)
+        if samples.size == 0:
+            return
+
+        # For unsigned formats, center the data
+        if sample_format == QAudioFormat.SampleFormat.UInt8:
+            samples = samples.astype(np.int16)
+            samples -= 128
+
+        # Compute RMS of the audio samples as float64 for precision
+        rms = np.sqrt(np.mean(samples.astype(np.float64) ** 2))
+
+        # Normalize RMS value based on the sample format
+        level = rms / normalization_factor
+
+        # Ensure level is within 0.0 to 1.0
+        level = min(max(level, 0.0), 1.0)
+
+        # Scale to 0-100
+        level_percent = level * 100
+
+        # Update the level bar widget
+        self.update_audio_level(level_percent)
+
+    def update_audio_level(self, level: int):
+        """
+        Update the audio level bar
+
+        :param level: audio level
+        """
+        if self.bar is not None:
+            self.bar.setLevel(level)
+
+    def reset_audio_level(self):
+        """Reset the audio level bar"""
+        if self.bar is not None:
+            self.bar.setLevel(0)
+
+    def save_audio_file(self, filename: str):
+        """
+        Save the recorded audio frames to a WAV file
+
+        :param filename: output file name
+        """
+        # Define the parameters for the WAV file
+        channels = self.actual_audio_format.channelCount()
+        sample_size = self.actual_audio_format.bytesPerSample()
+        frame_rate = self.actual_audio_format.sampleRate()
+
+        # Open the WAV file
+        wf = wave.open(filename, 'wb')
+        wf.setnchannels(channels)
+        wf.setsampwidth(sample_size)
+        wf.setframerate(frame_rate)
+
+        # Write frames to the file
+        wf.writeframes(b''.join(self.frames))
+        wf.close()
+
+    def get_dtype_from_sample_format(self, sample_format):
+        """
+        Get the NumPy dtype corresponding to the QAudioFormat sample format
+
+        :param sample_format: QAudioFormat.SampleFormat
+        """
+        if sample_format == QAudioFormat.SampleFormat.UInt8:
+            return np.uint8
+        elif sample_format == QAudioFormat.SampleFormat.Int16:
+            return np.int16
+        elif sample_format == QAudioFormat.SampleFormat.Int32:
+            return np.int32
+        elif sample_format == QAudioFormat.SampleFormat.Float:
+            return np.float32
+        else:
+            raise ValueError("Unsupported sample format")
+
+    def get_normalization_factor(self, sample_format):
+        """
+        Get the normalization factor for the QAudioFormat sample format
+
+        :param sample_format: QAudioFormat.SampleFormat
+        """
+        if sample_format == QAudioFormat.SampleFormat.UInt8:
+            return 255.0
+        elif sample_format == QAudioFormat.SampleFormat.Int16:
+            return 32768.0
+        elif sample_format == QAudioFormat.SampleFormat.Int32:
+            return float(2 ** 31)
+        elif sample_format == QAudioFormat.SampleFormat.Float:
+            return 1.0
+        else:
+            raise ValueError("Unsupported sample format")
+
+    def check_audio_input(self) -> bool:
+        """
+        Check if default audio input device is working
+
+        :return: True if working
+        """
+        import pyaudio
+        try:
+            rate = 44100
+            channels = 1
+            p = pyaudio.PyAudio()
+            stream = p.open(format=pyaudio.paInt16,
+                            channels=channels,
+                            rate=rate,
+                            input=True)
+            stream.stop_stream()
+            stream.close()
+            p.terminate()
+            return True
+        except Exception as e:
+            return False

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/src/pygpt_net/data/config/config.json

@@ -1,7 +1,7 @@
 {
   "__meta__": {
-    "version": "2.4.49",
-    "app.version": "2.4.49",
+    "version": "2.4.50",
+    "app.version": "2.4.50",
     "updated_at": "2025-01-16T00:00:00"
   },
   "access.audio.event.speech": false,

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/src/pygpt_net/data/config/models.json

@@ -1,7 +1,7 @@
 {
     "__meta__": {
-        "version": "2.4.49",
-        "app.version": "2.4.49",
+        "version": "2.4.50",
+        "app.version": "2.4.50",
         "updated_at": "2025-01-16T00:00:00"
     },
     "items": {

{pygpt_net-2.4.49 → pygpt_net-2.4.50}/src/pygpt_net/data/config/modes.json

@@ -1,7 +1,7 @@
 {
     "__meta__": {
-        "version": "2.4.49",
-        "app.version": "2.4.49",
+        "version": "2.4.50",
+        "app.version": "2.4.50",
         "updated_at": "2025-01-16T00:00:00"
     },
     "items": {