2.4.54

• Audio output switched from PyGame to PyAudio. It may be necessary to manually connect Alsa in Snap version with: "sudo snap connect pygpt:alsa".
• Added audio output volume progress bar.

2.4.53

• Fix: issue #89

2.4.52

• Improved audio input button visibility toggle.
• Fix: check for required arguments - issue #88.
• UI Fixes.

2.4.51

• 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

• Refactored audio input core.
• Added audio input volume progress bar.

2.4.49

• Fix: stream render in Assistants mode.
• Fix: items remove in context regen/edit.

2.4.48

• Fix: parsing lists in data loaders configuration.
• Fix: crash on Windows on PySide6 v6.6.0.
• Added Gemini embeddings to LlamaIndex settings.
• LlamaIndex upgraded to 0.12.11.
• Security updates.

2.4.47

• Added support for Python 3.12.
• Added a new model to Chat with Files: gemini-2.0-flash-exp.
• PySide6 upgraded to 6.6.0.

2.4.46

• Added a new tab in Settings: "API Keys", where the API keys configuration for Google and Anthropic models has been relocated.
• 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

• Enhanced web data loaders UI.