pygpt-net 2.5.2__py3-none-any.whl → 2.5.4__py3-none-any.whl

CHANGELOG.md

@@ -1,5 +1,17 @@
 # CHANGELOG
 
+## 2.5.4 (2025-02-02)
+
+- Added new models: `o3-mini` and `gpt-4o-mini-audio-preview`.
+- Enabled tool calls in Chat with Audio mode.
+- Added a check to verify if Ollama is running and if the model is available.
+
+## 2.5.3 (2025-02-01)
+
+- Fix: Snap permission denied bug.
+- Fix: column focus on tab change.
+- Datetime separators in groups moved to right side.
+
 ## 2.5.2 (2025-02-01)
 
 - Fix: spinner update after inline image generation.

README.md

@@ -2,7 +2,7 @@
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.5.2** | build: **2025.02.01** | Python: **>=3.10, <3.13**
+Release: **2.5.4** | build: **2025.02.02** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -284,6 +284,10 @@ To use microphone in Snap version you must connect the microphone with:
 sudo snap connect pygpt:audio-record :audio-record
 ```
 
+**Access to microphone and audio in Windows version:**
+
+If you have a problems with audio or microphone in the non-binary PIP/Python version on Windows, check to see if FFmpeg is installed. If it's not, install it and add it to the PATH. You can find a tutorial on how to do this here: https://phoenixnap.com/kb/ffmpeg-windows. The binary version already includes FFmpeg.
+
 **Windows and VC++ Redistributable**
 
 On Windows, the proper functioning requires the installation of the `VC++ Redistributable`, which can be found on the Microsoft website:
@@ -3960,6 +3964,18 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.5.4 (2025-02-02)**
+
+- Added new models: `o3-mini` and `gpt-4o-mini-audio-preview`.
+- Enabled tool calls in Chat with Audio mode.
+- Added a check to verify if Ollama is running and if the model is available.
+
+**2.5.3 (2025-02-01)**
+
+- Fix: Snap permission denied bug.
+- Fix: column focus on tab change.
+- Datetime separators in groups moved to right side.
+
 **2.5.2 (2025-02-01)**
 
 - Fix: spinner update after inline image generation.

pygpt_net/CHANGELOG.txt

@@ -1,3 +1,15 @@
+2.5.4 (2025-02-02)
+
+- Added new models: o3-mini and gpt-4o-mini-audio-preview.
+- Enabled tool calls in Chat with Audio mode.
+- Added a check to verify if Ollama is running and if the model is available.
+
+2.5.3 (2025-02-01)
+
+- Fix: Snap permission denied bug.
+- Fix: column focus on tab change.
+- Datetime separators in groups moved to right side.
+
 2.5.2 (2025-02-01)
 
 - Fix: spinner update after inline image generation.

pygpt_net/__init__.py

@@ -6,15 +6,15 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.02.01 02:00:00                  #
+# Updated Date: 2025.02.02 02:00:00                  #
 # ================================================== #
 
 __author__ = "Marcin Szczygliński"
 __copyright__ = "Copyright 2025, Marcin Szczygliński"
 __credits__ = ["Marcin Szczygliński"]
 __license__ = "MIT"
-__version__ = "2.5.2"
-__build__ = "2025.02.01"
+__version__ = "2.5.4"
+__build__ = "2025.02.02"
 __maintainer__ = "Marcin Szczygliński"
 __github__ = "https://github.com/szczyglis-dev/py-gpt"
 __report__ = "https://github.com/szczyglis-dev/py-gpt/issues"

pygpt_net/controller/chat/input.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.02.01 11:00:00                  #
+# Updated Date: 2025.02.02 02:00:00                  #
 # ================================================== #
 
 from typing import Optional, Any, Dict
@@ -74,12 +74,22 @@ class Input:
                 self.window.controller.agent.common.display_infinity_loop_confirm()
                 return
 
-            # TODO: check ollama status
-            """
-            if mode == MODE_LLAMA_INDEX:
-                status = self.window.core.models.ollama.get_status()
-                print("Ollama status: {}".format(status))
-            """
+            # check ollama model
+            model = self.window.core.config.get('model')
+            if mode == MODE_LLAMA_INDEX and model is not None:
+                model_data = self.window.core.models.get(model)
+                if model_data is not None and model_data.is_ollama():
+                    model_id = model_data.get_ollama_model()
+                    status = self.window.core.models.ollama.check_model(model_id)
+                    is_installed = status.get('is_installed', False)
+                    is_model = status.get('is_model', False)
+                    if not is_installed:
+                        self.window.ui.dialogs.alert(trans("dialog.ollama.not_installed"))
+                        return
+                    if not is_model:
+                        self.window.ui.dialogs.alert(
+                            trans("dialog.ollama.model_not_found").replace("{model}", model_id))
+                        return
 
         # listen for stop command
         if self.generating \

pygpt_net/controller/model/__init__.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.02.01 11:00:00                  #
+# Updated Date: 2025.02.02 02:00:00                  #
 # ================================================== #
 
 from typing import Optional
@@ -161,6 +161,7 @@ class Model:
             if "provider" in data[k].llama_index and data[k].llama_index["provider"] == "ollama":
                 suffix = " [Ollama]"
             items[k] = data[k].name + suffix
+        items = dict(sorted(items.items(), key=lambda item: item[1]))  # sort items by name
         self.window.ui.nodes["prompt.model"].set_keys(items)
 
     def update(self):

pygpt_net/controller/ui/tabs.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.17 13:00:00                  #
+# Updated Date: 2025.02.01 16:00:00                  #
 # ================================================== #
 
 from typing import Any, Optional
@@ -307,6 +307,8 @@ class Tabs:
 
         :param idx: column index
         """
+        if self.column_idx == idx:
+            return
         self.column_idx = idx
         self.on_column_changed()
         self.on_changed()

pygpt_net/core/command/__init__.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.02.01 11:00:00                  #
+# Updated Date: 2025.02.02 02:00:00                  #
 # ================================================== #
 
 import copy
@@ -587,7 +587,6 @@ class Command:
             MODE_LLAMA_INDEX,
             MODE_LANGCHAIN,
             MODE_COMPLETION,
-            MODE_AUDIO,
         ]
         mode = self.window.core.config.get('mode')
         if mode in disabled_modes:

pygpt_net/core/models/ollama.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.02.01 11:00:00                  #
+# Updated Date: 2025.02.02 02:00:00                  #
 # ================================================== #
 
 import requests
@@ -19,6 +19,7 @@ class Ollama:
         :param window: Window instance
         """
         self.window = window
+        self.available_models = []
 
     def get_status(self) -> dict:
         """
@@ -44,4 +45,39 @@ class Ollama:
             return {
                 'status': False,
                 'models': []
-            }
+            }
+
+    def check_model(self, model: str) -> dict:
+        """
+        Check if model is available
+
+        :param model: model ID
+        :return: dict
+        """
+        result = {
+            'is_installed': False,
+            'is_model': False,
+        }
+        if model in self.available_models:
+            return {
+                'is_installed': True,
+                'is_model': True,
+            }
+        status = self.get_status()
+        if not status.get('status'):
+            return result
+        if "models" not in status:
+            return result
+        for item in status.get('models', []):
+            model_id = item.get('name').replace(":latest", "")
+            if model_id not in self.available_models:
+                self.available_models.append(item.get('name'))  #
+            if model_id == model:
+                return {
+                    'is_installed': True,
+                    'is_model': True,
+                }
+        return {
+            'is_installed': True,
+            'is_model': False,
+        }

pygpt_net/data/config/config.json

@@ -1,8 +1,8 @@
 {
   "__meta__": {
-    "version": "2.5.2",
-    "app.version": "2.5.2",
-    "updated_at": "2025-02-01T00:00:00"
+    "version": "2.5.4",
+    "app.version": "2.5.4",
+    "updated_at": "2025-02-02T00:00:00"
   },
   "access.audio.event.speech": false,
   "access.audio.event.speech.disabled": [],

pygpt_net/data/config/models.json

@@ -1,8 +1,8 @@
 {
     "__meta__": {
-        "version": "2.5.2",
-        "app.version": "2.5.2",
-        "updated_at": "2025-02-01T00:00:00"
+        "version": "2.5.4",
+        "app.version": "2.5.4",
+        "updated_at": "2025-02-02T00:00:00"
     },
     "items": {
         "claude-3-5-sonnet-20240620": {
@@ -1708,6 +1708,79 @@
             "default": false,
             "multimodal": []
         },
+        "gpt-4o-mini-audio-preview": {
+            "id": "gpt-4o-mini-audio-preview",
+            "name": "gpt-4o-mini-audio-preview",
+            "mode": [
+                "audio"
+            ],
+            "langchain": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model_name",
+                        "value": "gpt-4o-mini-audio-preview",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "llama_index": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model",
+                        "value": "gpt-4o-mini-audio-preview",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "ctx": 128000,
+            "tokens": 16384,
+            "default": false,
+            "multimodal": []
+        },
         "gpt-4o-2024-11-20": {
             "id": "gpt-4o-2024-11-20",
             "name": "gpt-4o-2024-11-20",
@@ -2426,7 +2499,7 @@
                 ]
             },
             "ctx": 128000,
-            "tokens": 4096,
+            "tokens": 65536,
             "default": false
         },
         "o1-mini": {
@@ -2500,7 +2573,7 @@
                 ]
             },
             "ctx": 128000,
-            "tokens": 4096,
+            "tokens": 65536,
             "default": false
         },
         "o1": {
@@ -2575,10 +2648,244 @@
                 ]
             },
             "ctx": 128000,
-            "tokens": 4096,
+            "tokens": 100000,
             "default": false,
             "multimodal": []
         },
+        "o3-mini-low": {
+            "id": "o3-mini",
+            "name": "o3-mini (low)",
+            "mode": [
+                "chat",
+                "agent",
+                "expert"
+            ],
+            "langchain": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model_name",
+                        "value": "o3-mini",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "llama_index": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model",
+                        "value": "o3-mini",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "ctx": 200000,
+            "tokens": 100000,
+            "default": false,
+            "multimodal": [],
+            "extra": {
+                "reasoning_effort": "low"
+            }
+        },
+        "o3-mini-medium": {
+            "id": "o3-mini",
+            "name": "o3-mini (medium)",
+            "mode": [
+                "chat",
+                "agent",
+                "expert"
+            ],
+            "langchain": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model_name",
+                        "value": "o3-mini",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "llama_index": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model",
+                        "value": "o3-mini",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "ctx": 200000,
+            "tokens": 100000,
+            "default": false,
+            "multimodal": [],
+            "extra": {
+                "reasoning_effort": "medium"
+            }
+        },
+        "o3-mini-high": {
+            "id": "o3-mini",
+            "name": "o3-mini (high)",
+            "mode": [
+                "chat",
+                "agent",
+                "expert"
+            ],
+            "langchain": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model_name",
+                        "value": "o3-mini",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "llama_index": {
+                "provider": "openai",
+                "mode": [
+                    "chat"
+                ],
+                "args": [
+                    {
+                        "name": "model",
+                        "value": "o3-mini",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "ctx": 200000,
+            "tokens": 100000,
+            "default": false,
+            "multimodal": [],
+            "extra": {
+                "reasoning_effort": "high"
+            }
+        },
         "bielik-11b-v2.2-instruct:Q4_K_M": {
             "id": "SpeakLeash/bielik-11b-v2.2-instruct:Q4_K_M",
             "name": "bielik-11b-v2.2",

pygpt_net/data/config/modes.json

@@ -1,8 +1,8 @@
 {
     "__meta__": {
-        "version": "2.5.2",
-        "app.version": "2.5.2",
-        "updated_at": "2025-02-01T00:00:00"
+        "version": "2.5.4",
+        "app.version": "2.5.4",
+        "updated_at": "2025-02-02T00:00:00"
     },
     "items": {
         "chat": {

pygpt_net/data/locale/locale.de.ini

@@ -293,6 +293,8 @@ dialog.license.label = Durch die Verwendung dieser Software akzeptieren Sie die
 dialog.license.title = Lizenz
 dialog.logger.btn.clear = Löschen
 dialog.logger.title = Protokollierung
+dialog.ollama.model_not_found = Das angeforderte Modell ({model}) ist in deinem Ollama nicht verfügbar.\nBitte lade das Modell herunter, indem du den Befehl ausführst:\nollama pull {model}
+dialog.ollama.not_installed = Ollama ist nicht installiert oder läuft nicht.\nBitte installiere zuerst Ollama, indem du die folgende Seite besuchst:\nhttps://ollama.com/download
 dialog.plugin_settings = Plugin-Einstellungen
 dialog.plugin.settings.btn.defaults.app = Standardwerte laden
 dialog.plugin.settings.btn.defaults.user = Änderungen rückgängig machen
@@ -778,8 +780,8 @@ settings.audio.input.rate.desc = Abtastrate, Standard: 44100
 settings.audio.input.stop_interval = Intervall für kontinuierliche automatische Transkription
 settings.audio.input.stop_interval.desc = Intervall in Sekunden für automatisches Transkribieren eines Audioabschnitts, Standard: 10
 settings.audio.input.timeout = Aufnahme-Zeitüberschreitung
-settings.audio.input.timeout.desc = Zeitüberschreitung (Sekunden) für automatische Stop-Aufzeichnung, 0 zum Deaktivieren, Standard: 120
 settings.audio.input.timeout.continuous = Zeitüberschreitung im Dauerbetrieb aktivieren
+settings.audio.input.timeout.desc = Zeitüberschreitung (Sekunden) für automatische Stop-Aufzeichnung, 0 zum Deaktivieren, Standard: 120
 settings.check_updates = Beim Start nach Updates suchen
 settings.check_updates.bg = Im Hintergrund nach Updates suchen
 settings.cmd.field.desc = Aktivieren Sie das `{cmd}`-Werkzeug.

pygpt_net/data/locale/locale.en.ini

@@ -325,6 +325,8 @@ dialog.models.editor.defaults.app.result = Restored to models factory settings.
 dialog.models.editor.defaults.user.confirm = Undo current changes?
 dialog.models.editor.defaults.user.result = Restored models user config
 dialog.models.editor.delete.confirm = Are you sure you want to delete the model?
+dialog.ollama.model_not_found = The requested model ({model}) is not available in your Ollama.\nPlease download the model first by executing the command:\nollama pull {model}
+dialog.ollama.not_installed = Ollama is not installed or not running.\nPlease install Ollama first by visiting:\nhttps://ollama.com/download
 dialog.plugin_settings = Plugin settings
 dialog.plugin.settings.btn.defaults.app = Load defaults
 dialog.plugin.settings.btn.defaults.user = Undo changes
@@ -952,8 +954,8 @@ settings.audio.input.rate.desc = Sampling rate, default: 44100
 settings.audio.input.stop_interval = Continuous recording auto-transcribe interval
 settings.audio.input.stop_interval.desc = Interval in seconds for auto-transcribe audio chunk, default: 10
 settings.audio.input.timeout = Recording timeout
-settings.audio.input.timeout.desc = Timeout (seconds) for auto-stop recording, 0 to disable, default: 120
 settings.audio.input.timeout.continuous = Enable timeout in continuous mode
+settings.audio.input.timeout.desc = Timeout (seconds) for auto-stop recording, 0 to disable, default: 120
 settings.check_updates = Check for Updates on start
 settings.check_updates.bg = Check for Updates in the background
 settings.cmd.config.collapse = JSON params
@@ -1117,10 +1119,10 @@ settings.section.agent.llama = Agents
 settings.section.api_keys = API Keys
 settings.section.api_keys.anthropic = Anthropic
 settings.section.api_keys.azure_openai = Azure OpenAI
+settings.section.api_keys.deepseek = DeepSeek
 settings.section.api_keys.google = Google
 settings.section.api_keys.huggingface = HuggingFace
 settings.section.api_keys.openai = OpenAI
-settings.section.api_keys.deepseek = DeepSeek
 settings.section.audio = Audio
 settings.section.ctx = Context
 settings.section.developer = Developer