Python Qt6 : test from PNG to SVG with potrace ...

Tests from two days ago with conversion from PNG format to SVG format with the python potrace package ...

Python Qt6 : use default PyQt styles to PyQt6 applications.

Today, about PyQt Styles to PyQt6 Applications.

This works with default themes and how to change these, and using different types of custom styling.

First , let's see the source code with default themes:

from PyQt6.QtWidgets import QStyleFactory
print(QStyleFactory.keys())
['windows11', 'windowsvista', 'Windows', 'Fusion']

Let's see the source code for this simple script with this theme windows11:

import sys
from PyQt6.QtWidgets import (
    QApplication, QLabel, QLineEdit, QComboBox, QPushButton,
    QCheckBox, QSlider, QVBoxLayout, QWidget
)
from PyQt6.QtCore import Qt

app = QApplication(sys.argv)
app.setStyle('windows11')

window = QWidget()
layout = QVBoxLayout(window)

# 1. QLabel
layout.addWidget(QLabel("Acesta este un QLabel"))

# 2. QLineEdit
layout.addWidget(QLineEdit("Text editabil"))

# 3. QComboBox
combo = QComboBox()
combo.addItems(["Optiunea 1", "Optiunea 2", "Optiunea 3"])
layout.addWidget(combo)

# 4. QCheckBox
layout.addWidget(QCheckBox("Bifează această opțiune"))

# 5. QSlider
slider = QSlider(Qt.Orientation.Horizontal)
layout.addWidget(slider)

# 5. QPushButton
button = QPushButton('Simple button !')
layout.addWidget(button)

# show the main windows 
window.show()
sys.exit(app.exec())

Python Qt6 : Check certificate of url.

Today, I will show this python script to check the certificate of url.

import sys
import ssl
import socket
from datetime import datetime

from cryptography import x509
from cryptography.hazmat.backends import default_backend

from PyQt6.QtWidgets import (
    QApplication, QWidget, QVBoxLayout, QLabel,
    QLineEdit, QPushButton, QTextEdit
)

def fetch_certificate_raw(hostname):
    """
    Connects to the server and retrieves the certificate in DER format.
    Also returns a validation status message.
    """

    # Create a default SSL context (validates certificates)
    context = ssl.create_default_context()

    try:
        # First attempt: strict validation
        with socket.create_connection((hostname, 443), timeout=5) as sock:
            with context.wrap_socket(sock, server_hostname=hostname) as ssock:
                der_cert = ssock.getpeercert(binary_form=True)
                return der_cert, "Certificate is VALID"

    except ssl.SSLError as e:
        # Certificate is invalid → try to retrieve it anyway
        try:
            unverified_context = ssl._create_unverified_context()
            with socket.create_connection((hostname, 443), timeout=5) as sock:
                with unverified_context.wrap_socket(sock, server_hostname=hostname) as ssock:
                    der_cert = ssock.getpeercert(binary_form=True)
                    return der_cert, f"Certificate is INVALID: {str(e)}"
        except Exception:
            return None, f"Could not retrieve certificate: {str(e)}"

    except Exception as e:
        return None, f"Connection error: {str(e)}"

def parse_certificate(der_cert):
    """
    Converts a DER-encoded certificate into a cryptography.x509 object.
    """
    return x509.load_der_x509_certificate(der_cert, default_backend())

class CertViewer(QWidget):
    """
    Main GUI window for the HTTPS certificate viewer.
    """
    def __init__(self):
        super().__init__()

        self.setWindowTitle("HTTPS Certificate Checker")
        self.setGeometry(200, 200, 700, 600)

        layout = QVBoxLayout()

        # Input label + text field
        layout.addWidget(QLabel("Enter URL (example: example.com):"))
        self.input = QLineEdit()
        layout.addWidget(self.input)

        # Button to trigger certificate check
        self.button = QPushButton("Check Certificate")
        self.button.clicked.connect(self.check_certificate)
        layout.addWidget(self.button)

        # Output text box
        self.output = QTextEdit()
        self.output.setReadOnly(True)
        layout.addWidget(self.output)

        self.setLayout(layout)

    def check_certificate(self):
        """
        Triggered when the user presses the button.
        Retrieves and displays certificate information.
        """

        hostname = self.input.text().strip()

        # Clean URL (remove http://, https://, and paths)
        for prefix in ("https://", "http://"):
            if hostname.startswith(prefix):
                hostname = hostname[len(prefix):]

        hostname = hostname.split("/")[0]

        # Fetch certificate
        der_cert, status = fetch_certificate_raw(hostname)

        if der_cert is None:
            self.output.setText(status)
            return

        # Parse certificate
        cert = parse_certificate(der_cert)

        # Build output text
        text = f"=== CERTIFICATE STATUS ===\n{status}\n\n"
        text += "=== CERTIFICATE DETAILS ===\n\n"

        text += f"Subject:\n{cert.subject}\n\n"
        text += f"Issuer:\n{cert.issuer}\n\n"
        text += f"Serial Number: {cert.serial_number}\n\n"
        text += f"Version: {cert.version}\n\n"
        text += f"Valid From: {cert.not_valid_before}\n"
        text += f"Valid To:   {cert.not_valid_after}\n\n"

        # Check expiration
        if cert.not_valid_after < datetime.utcnow():
            text += f"⚠ Certificate EXPIRED on: {cert.not_valid_after}\n\n"

        # Subject Alternative Names (SAN)
        try:
            san = cert.extensions.get_extension_for_class(x509.SubjectAlternativeName)
            text += f"Subject Alternative Names:\n{san.value}\n\n"
        except Exception:
            text += "Subject Alternative Names: (none)\n\n"

        self.output.setText(text)

if __name__ == "__main__":
    app = QApplication(sys.argv)
    viewer = CertViewer()
    viewer.show()
    sys.exit(app.exec())

Python 3.13.0 : PyWin32 is full compatible with Python 3.13 .

Today I tried to use these python packages:

import win32serviceutil
import win32service
import win32event
import servicemanager

The works , but python -m pywin32_postinstall -install comes with:

python.exe: No module named pywin32_postinstall

NOTE : The copilot artificial intelligence, search and give me an old answer , but is wrong ...

PyWin32 is updated slowly, and at this moment there are no wheels for Python 3.13.

The pip tool cannot install pywin32 does not install anything usable, and pywin32_postinstall does not exist

Possible solutions

PyWin32 works perfectly on:

• Python 3.12
• Python 3.11
• Python 3.10

If you need win32service, win32api, win32com, etc., you must use a supported version.

Need to see the last tutorial from my blogger.

I tested on admin with simple service and works:

python service_test_001.py install
Installing service MyPythonService
Service installed

This is the source code:

import win32serviceutil
import win32service
import win32event
import servicemanager
import time

class MyService(win32serviceutil.ServiceFramework):
    _svc_name_ = "MyPythonService"
    _svc_display_name_ = "My Python Windows Service"
    _svc_description_ = "A minimal Windows service example written in Python."

    def __init__(self, args):
        win32serviceutil.ServiceFramework.__init__(self, args)
        self.stop_event = win32event.CreateEvent(None, 0, 0, None)
        self.running = True

    def SvcStop(self):
        self.ReportServiceStatus(win32service.SERVICE_STOP_PENDING)
        win32event.SetEvent(self.stop_event)
        self.running = False

    def SvcDoRun(self):
        servicemanager.LogInfoMsg("MyPythonService is starting.")
        self.main()

    def main(self):
        while self.running:
            # Your service logic goes here
            time.sleep(5)
            servicemanager.LogInfoMsg("MyPythonService heartbeat.")


if __name__ == '__main__':
    win32serviceutil.HandleCommandLine(MyService)

Python 3.13.0 : how to install pywin32_postinstall.

Today a tutorial on how to install pywin32_postinstall.

This package is essential for accessing Windows-specific functionalities in Python.

The pywin32_postinstall missing python error typically occurs when the pywin32 package is not properly installed or the post-installation script is not executed correctly.

Fisrt install the pywin32 python package.

pip install pywin32

The next step is to run this command on the path with Script folder.

python C:\Python313\Scripts\pywin32_postinstall.py -install
Parsed arguments are: Namespace(install=True, remove=False, wait=None, silent=False, quiet=False, destination= ...

The next step is to run this command on the path with Script folder.

D:\Python313_64bit>python
Python 3.13.0 (tags/v3.13.0:60403a5, Oct  7 2024, 09:38:07) [MSC v.1941 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import win32api
>>> print(win32api.GetVersion())

Python 3.12.12 : simple example with CompVis/stable-diffusion-v1-4 model on colab.

Because this year we need to start it as advanced and more prepared as we know and can do ...

Today I tested a simple source code with an interactive interface for text-to-image generation based on the CompVis/stable-diffusion-v1-4 model.

This is not an advanced model and you will have some dizzy images, but the learnning idea is the base of these colabs notebooks.

See the default example on my colab github project.

The colab notebook use this python version:

Python 3.12.12 (main, Oct 10 2025, 08:52:57) [GCC 11.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.

I'm mode advanced with some models like SDXL, image generation is not a priority at the moment ...

... and first image result is this:

Python Qt6 : ... tool for testing fonts.

Today I created a small Python script with PyQt6 using artificial intelligence. It is a tool that takes a folder of fonts, allows to select their size, displays the font size in pixels for Label text from the Godot engine and downloads only the selection of fonts that I like. I have not tested it to see the calculations with Godot, but it seems functional...

Python Qt6 : ... search custom data in files with python and PyQt6.

The other day I noticed that I can't find what I worked on in the past, some files were blocked... Another task was blocking the artificial intelligence due to the number of uses. I could have used artificial intelligence to open old projects and ask where what I worked on is, but it would be a risk to waste my queries. Since I always use a specific signature when working on separate projects and the backup is distributed on storage that is always filling up, I created a simple script that would search for my custom with custom files, custom content and output a spreader with them. Here is the result of a 310-line source code script, obviously created with artificial intelligence.

Python 3.13.0 : ... simple script for copilot history.

NOTES: I have been using artificial intelligence since it appeared, it is obviously faster and more accurate, I recommend using testing on larger projects.

See this article

This python script will take the database and use to get copilot history and save to file copilot_conversations.txt :

import os
import sqlite3
import datetime
import requests
from bs4 import BeautifulSoup
import shutil

# Locația tipică pentru istoricul Edge (Windows)
edge_history_path = os.path.expanduser(
    r"~\\AppData\\Local\\Microsoft\\Edge\\User Data\\Default\\History"
)

# Copiem fișierul History în folderul curent
def copy_history_file(src_path, dst_name="edge_history_copy.db"):
    if not os.path.exists(src_path):
        print("Nu am găsit istoricul Edge.")
        return None
    dst_path = os.path.join(os.getcwd(), dst_name)
    try:
        shutil.copy(src_path, dst_path)
        print(f"Am copiat baza de date în {dst_path}")
        return dst_path
    except Exception as e:
        print(f"Eroare la copiere: {e}")
        return None

def extract_copilot_links(db_path):
    conn = sqlite3.connect(db_path)
    cursor = conn.cursor()

    cursor.execute("""
        SELECT url, title, last_visit_time
        FROM urls
        WHERE url LIKE '%copilot%'
    """)

    results = []
    for url, title, last_visit_time in cursor.fetchall():
        ts = datetime.datetime(1601, 1, 1) + datetime.timedelta(microseconds=last_visit_time)
        results.append({
            "url": url,
            "title": title,
            "last_visit": ts.strftime("%Y-%m-%d %H:%M:%S")
        })

    conn.close()
    return results

def fetch_conversation(url):
    try:
        resp = requests.get(url)
        if resp.status_code == 200:
            soup = BeautifulSoup(resp.text, "html.parser")
            texts = soup.get_text(separator="\n", strip=True)
            return texts
        else:
            return f"Eroare acces {url}: {resp.status_code}"
    except Exception as e:
        return f"Eroare acces {url}: {e}"

if __name__ == "__main__":
    copy_path = copy_history_file(edge_history_path)
    if copy_path:
        chats = extract_copilot_links(copy_path)
        if chats:
            with open("copilot_conversations.txt", "w", encoding="utf-8") as f:
                for chat in chats:
                    content = fetch_conversation(chat["url"])
                    f.write(f"=== Conversație: {chat['title']} ({chat['last_visit']}) ===\n")
                    f.write(content)
                    f.write("\n\n")
            print("Am salvat conversațiile în copilot_conversations.txt")
        else:
            print("Nu am găsit conversații Copilot în istoricul Edge.")

Python Qt6 : ... data generator tool for a custom format file.

Today I finished a data generator tool for a custom format for a game. The idea is that PyQt6 is versatile and very useful for a developer. This tool generates data in the 2D area of a screen and saves them in a defined format, in this case a position and a size for a text ...

Here is the class for custom range selection sliders.

class RangeSlider(QWidget):
    def __init__(self, parent=None):
        super().__init__(parent)
        self._min, self._max = 0, 1000
        self._start, self._end = 0, 1000
        self._dragging = None
        self.setMinimumHeight(24)

    def setRange(self, minimum, maximum):
        self._min, self._max = minimum, maximum
        self._start, self._end = minimum, maximum
        self.update()

    def setStart(self, val):
        self._start = max(self._min, min(val, self._end))
        self.update()

    def setEnd(self, val):
        self._end = min(self._max, max(val, self._start))
        self.update()

    def start(self): return self._start
    def end(self): return self._end

    def _pos_to_val(self, x):
        w = self.width()
        ratio = max(0, min(x, w)) / w if w else 0
        return int(self._min + ratio*(self._max-self._min))

    def _val_to_pos(self, val):
        w = self.width()
        return int((val-self._min)/(self._max-self._min)*w) if self._max>self._min else 0

    def mousePressEvent(self, e):
        x = e.position().x()
        sx, ex = self._val_to_pos(self._start), self._val_to_pos(self._end)
        self._dragging = "start" if abs(x-sx)<abs(x-ex) else "end"
        self.mouseMoveEvent(e)

    def mouseMoveEvent(self, e):
        if self._dragging:
            val = self._pos_to_val(int(e.position().x()))
            if self._dragging=="start": self.setStart(val)
            else: self.setEnd(val)

    def mouseReleaseEvent(self,e): self._dragging=None

    def paintEvent(self,e):
        p=QPainter(self); rect=self.rect()
        sx,ex=self._val_to_pos(self._start),self._val_to_pos(self._end)
        p.fillRect(rect,QColor(220,220,220))
        p.fillRect(QRect(QPoint(sx,0),QPoint(ex,rect.height())),QColor(100,200,100,120))
        p.setBrush(QColor(50,120,200)); p.setPen(Qt.PenStyle.NoPen)
        p.drawEllipse(QPoint(sx,rect.center().y()),6,6)
        p.drawEllipse(QPoint(ex,rect.center().y()),6,6)

Python 3.13.0 : xAI A.P.I. with regional endpoint on xai_sdk python package.

Grok is a family of Large Language Models (LLMs) developed by xAI.

Inspired by the Hitchhiker's Guide to the Galaxy, Grok is a maximally truth-seeking AI that provides insightful, unfiltered truths about the universe.

xAI offers an API for developers to programmatically interact with our Grok models. The same models power our consumer facing services such as Grok.com, the iOS and Android apps, as well as Grok in X experience.

If you want to use a regional endpoint, you need to specify the endpoint url when making request with SDK. In xAI SDK, this is specified through the api_host parameter.

Is not free models available for xAI A.P.I.

See this example from the official website:

import os

from xai_sdk import Client
from xai_sdk.chat import user

client = Client(
api_key=os.getenv("XAI_API_KEY"),
api_host="us-east-1.api.x.ai" # Without the https://
)

chat = client.chat.create(model="grok-4")
chat.append(user("What is the meaning of life?"))

completion = chat.sample()

Python Qt6 : tool for remove duplicate files ...

Today I created a Python script with PyQt6 that allows me to remove duplicate files based on three ways of selecting the type of duplicate.

The script also makes an estimate of the execution time...

Because the source code is relatively simple and can be very easily reconstructed with the help of artificial intelligence, I am not adding it to the posts.

Here is what the application looks like with PyQt6.

Python Qt6 : tool for cutting images ...

Today I made a script that allows adding custom horizontal and vertical sliders to an image and, depending on the custom distance between them, cuts the image into squares of different sizes.

Python Qt6 : tool for renaming files with creation date .

Since this hacking and the crashes... I've always taken screenshots... Today I created a small script that takes files from a folder and renames them with the creation date in this format...yyyyMMdd_HHmmss .

... obviously artificial intelligence helped me.

This is the source code :

import sys
import os
import shutil
from PyQt6.QtWidgets import QApplication, QWidget, QPushButton, QVBoxLayout, QFileDialog, QMessageBox
from PyQt6.QtCore import QDateTime

class FileRenamer(QWidget):
    def __init__(self):
        super().__init__()
        self.setWindowTitle("Redenumire fișiere cu dată și index")
        self.setGeometry(100, 100, 400, 150)

        layout = QVBoxLayout()

        self.button = QPushButton("Selectează folderul și redenumește fișierele")
        self.button.clicked.connect(self.rename_files)
        layout.addWidget(self.button)

        self.setLayout(layout)

    def rename_files(self):
        folder = QFileDialog.getExistingDirectory(self, "Selectează folderul")
        if not folder:
            return

        files = [f for f in os.listdir(folder) if os.path.isfile(os.path.join(folder, f))]
        files.sort()  # Sortează pentru consistență

        for index, filename in enumerate(files, start=1):
            old_path = os.path.join(folder, filename)
            try:
                creation_time = os.path.getctime(old_path)
                dt = QDateTime.fromSecsSinceEpoch(int(creation_time))
                date_str = dt.toString("yyyyMMdd_HHmmss")
                ext = os.path.splitext(filename)[1]
                new_name = f"{date_str}_{index:03d}{ext}"
                new_path = os.path.join(folder, new_name)

                # Evită suprascrierea fișierelor existente
                if not os.path.exists(new_path):
                    shutil.move(old_path, new_path)
            except Exception as e:
                QMessageBox.critical(self, "Eroare", f"Eroare la fișierul {filename}:\n{str(e)}")
                continue

        QMessageBox.information(self, "Succes", "Fișierele au fost redenumite cu succes!")

if __name__ == "__main__":
    app = QApplication(sys.argv)
    window = FileRenamer()
    window.show()
    sys.exit(app.exec())

Python Qt6 : tool for game development with PNG images.

Today, I worked with art artificial intelligence, to create tool for my game development.

I used python and PyQt6 and this tool help me to remove border, resize, split, rename and save images as PNG file type for Godot game engine.

Python 3.11.11 : Colab simple image to video with stabilityai - part 052.

Today, a simple test with artificial intelligence and stabilityai/stable-video-diffusion-img2vid-xt.

The result is not very good, but I believe the source code can be improved ...

pipe = StableVideoDiffusionPipeline.from_pretrained(
    'stabilityai/stable-video-diffusion-img2vid-xt',
    torch_dtype=torch.float16,
    variant='fp16'
)

pipe.enable_model_cpu_offload()

You can find the source code on my colab GitHUb projects - catafest_069.

Python 3.13.3 : ... Nuitka package works with python 3.12 and MinGW.

Nuitka is licensed under the Apache License, Version 2.0; you may not use it except in compliance with the License.

Nuitka is the Python compiler. It is written in Python. It is a seamless replacement or extension to the Python interpreter and compiles every construct that Python 2 (2.6, 2.7) and Python 3 (3.4 - 3.13) have, when itself run with that Python version.

Nuitka translates the Python modules into a C level program that then uses libpython and static C files of its own to execute in the same way as CPython does.

I used the pip command:

python -m pip install -U nuitka
Collecting nuitka
  Downloading Nuitka-2.7.tar.gz (3.9 MB)
...
Successfully built nuitka
Installing collected packages: zstandard, ordered-set, nuitka
Successfully installed nuitka-2.7 ordered-set-4.1.0 zstandard-0.23.0

[notice] A new release of pip is available: 25.0.1 -> 25.1.1
[notice] To update, run: python.exe -m pip install --upgrade pip

This version of python : 3.13.0rc1 not work !!!

I need to upgrade my version to 3.13.3 version today after I open an issue on github repo!

python.exe -m pip install --upgrade pip
...
Successfully installed pip-25.1.1

python -m nuitka --version
2.7
Commercial: None
Python: 3.13.0rc1 (tags/v3.13.0rc1:e4a3e78, Jul 31 2024, 20:58:38) [MSC v.1940 64 bit (AMD64)]
Flavor: CPython Official
GIL: yes
Executable: C:\Python313\python.exe
OS: Windows
Arch: x86_64
WindowsRelease: 10
Nuitka-Scons:WARNING: Windows SDK must be installed in Visual Studio for it to be usable
Nuitka-Scons:WARNING: with Nuitka. Use the Visual Studio installer for adding it.
Version C compiler: ~\AppData\Local\Nuitka\Nuitka\Cache\downloads\gcc\x86_64\14.2.0posix-19.1.1-12.0.0-msvcrt-r2\mingw64\bin\gcc.exe (gcc 14.2.0).

After upgrade the nuitka show me these results:

python -m nuitka --version
2.7
Commercial: None
Python: 3.13.3 (tags/v3.13.3:6280bb5, Apr  8 2025, 14:47:33) [MSC v.1943 64 bit (AMD64)]
Flavor: CPython Official
GIL: yes
Executable: C:\Python313\python.exe
OS: Windows
Arch: x86_64
WindowsRelease: 10
Nuitka-Scons:WARNING: Windows SDK must be installed in Visual Studio for it to be usable
Nuitka-Scons:WARNING: with Nuitka. Use the Visual Studio installer for adding it.
Version C compiler: ~\AppData\Local\Nuitka\Nuitka\Cache\downloads\gcc\x86_64\14.2.0posix-19.1.1-12.0.0-msvcrt-r2\mingw64\bin\gcc.exe (gcc 14.2.0).

Same error, I uninstall the Python: 3.13.3 version and I install the python version 3.13.0 and use the pip again to install this python package.

python -m pip install -U nuitka
Collecting nuitka
...
Installing collected packages: zstandard, ordered-set, nuitka
Successfully installed nuitka-2.7 ordered-set-4.1.0 zstandard-0.23.0

[notice] A new release of pip is available: 24.2 -> 25.1.1
[notice] To update, run: python.exe -m pip install --upgrade pip
python.exe -m pip install --upgrade pip
Requirement already satisfied: pip in c:\python_3_13_0\lib\site-packages (24.2)
...
Successfully installed pip-25.1.1

Using this version tell me same error with Windows and Visual Studio, but the MinGW is install from the first version.

The solution from artificial intelligence is to use another python version.

I used these commands:

py -3.12 -m pip install -U nuitka
Collecting nuitka
  Using cached Nuitka-2.7.tar.gz (3.9 MB)
  Installing build dependencies ... done
  ...
  Installing collected packages: zstandard, ordered-set, nuitka
Successfully installed nuitka-2.7 ordered-set-4.1.0 zstandard-0.23.0

[notice] A new release of pip is available: 24.2 -> 25.1.1
[notice] To update, run: C:\Python312\python.exe -m pip install --upgrade pip
py -0
 -V:3.13 *        Python 3.13 (64-bit)
 -V:3.12          Python 3.12 (64-bit)
py -3.12 -m nuitka --mingw64 hello.py
Nuitka-Options: Used command line options:
Nuitka-Options:   --mingw64 hello.py
Nuitka-Options:WARNING: You did not specify to follow or include anything but main
Nuitka-Options:WARNING: program. Check options and make sure that is intended.
Nuitka: Starting Python compilation with:
Nuitka:   Version '2.7' on Python 3.12 (flavor 'CPython Official')
Nuitka:   commercial grade 'not installed'.
Nuitka: Completed Python level compilation and optimization.
Nuitka: Generating source code for C backend compiler.
Nuitka: Running data composer tool for optimal constant value handling.
Nuitka: Running C compilation via Scons.
Nuitka-Scons: Backend C compiler: gcc (gcc 14.2.0).
Nuitka-Scons: Backend C linking with 6 files (no progress information available for
Nuitka-Scons: this stage).
Nuitka-Scons: Compiled 6 C files using ccache.
Nuitka-Scons: Cached C files (using ccache) with result 'cache miss': 6
Nuitka: Keeping build directory 'hello.build'.
Nuitka: Successfully created 'D:\PythonProjects\hello.exe'.
Nuitka: Execute it by launching 'hello.cmd', the batch file needs to set environment.

The test is a simple python script from the official website:

def talk(message):
    return "Talk " + message

def main():
    print(talk("Hello World"))

if __name__ == "__main__":
    main()

... and this python version works well with MinGW, the artificial intelligence used to fix these errors was ChatGPT.

hello.exe
Talk Hello World

Python 3.13.0rc1 : ... fal artificial intelligence and python test.

We have the most-popular models implemented and available as API endpoints for you to start crafting your own AI-powered app today. From the fal.ai website !

You need to set your A.P.I. key from this url.

system32>setx.exe FAL_KEY "e6fd708c-8065-4c73-ac2a-e3c73c6ff0fe:f70e0adb08362a3073993efa31b6acee"

SUCCESS: Specified value was saved.

Open a new terminal and with your editor create this simple example ...

import fal_client

response = fal_client.run("fal-ai/fast-sdxl", arguments={"prompt": "a cute cat, realistic, orange"})
print(response["images"][0]["url"])

Into the terminal run the python script and you will find the url of the image :

python test_fal_client_001.py
https://v3.fal.media/files/rabbit/kY2MZG6LLkzjyIT8J3oiI.jpe

This is the result output of the running source code as 1024px image, see the resize 112px I created:

Python 3.13.0rc1 : pig for AI-powered automation.

Pig is an API for AI-powered automation of Windows desktop applications and workflows. It allows AI agents to remotely navigate user interfaces and interact with software on Windows computers, even for applications without public APIs. Organizations might use Pig to automate complex, repetitive tasks involving legacy enterprise software, overcome limitations of traditional robotic process automation tools, and reduce the need for manual data handling by human workers.

Follow the install from the official website.

pip install pig-python
Collecting pig-python
...
Successfully installed aiohttp-retry-2.9.1 click-8.1.8 iso8601-2.1.0 pig-python-0.1.2 simple-term-menu-1.6.6 tabulate-0.9.0

From the API Keys url get the key and run a server:

piglet join --secret the_API_key
Display dimensions: 1280x720
Local server running at http://localhost:3000
Connected to control server

The local machine can be found on this webpage.

I go to machine chat and I ask to create a source script in python for test the artificial intelligence.

It looks like you're encountering an error with the Pig API. The error message indicates that the API key hasn't been set properly. To resolve this issue, you need to set the PIG_SECRET_KEY environment variable or pass the API key directly to the Client constructor when initializing the Pig client. Would you like me to help you with setting up the environment variable or modifying your code to include the API key in the Client constructor? yes , I need a python script example

The remote artificial intelligence machine move the mouse and open notepad, add source code and save to my desktop.

I add my API key and I run it, see the result:

This source script is the result of artificial intelligence processing

"""
Example script showing how to properly initialize the Pig client with an API key
using both environment variable and direct constructor methods.
"""

import os
from pig import Client

# Example API key (replace with your actual API key in production)
API_KEY = "SK-..."

def initialize_with_env_variable():
    """
    Method 1: Initialize Pig client using environment variable
    This is the recommended approach for production environments
    """
    # Set the environment variable
    os.environ["PIG_SECRET_KEY"] = API_KEY
    
    # Initialize the client (it will automatically use the environment variable)
    client = Client()
    
    print("Client initialized using environment variable")
    return client

def initialize_with_direct_key():
    """
    Method 2: Initialize Pig client by passing the API key directly
    Useful for testing or when environment variables are not preferred
    """
    # Initialize the client by passing the API key directly to the constructor
    client = Client(api_key=API_KEY)
    
    print("Client initialized by passing API key directly")
    return client

if __name__ == "__main__":
    # Example 1: Using environment variable
    client1 = initialize_with_env_variable()
    
    # Example 2: Passing API key directly
    client2 = initialize_with_direct_key()
    
    # Both methods achieve the same result
    print("Both initialization methods are complete!")

News : Ollama-Adaptive-Image-Code-Gen project test - need more memory.

Python code that leverages a language model (such as LLaMA) to generate images featuring basic shapes in 2D or 3D. The script randomly selects shapes, colors, and areas to create diverse visuals. It continuously generates images based on AI-generated code, validates them, and provides feedback for iterative improvements.

This source code can be found on this GitHub project named Ollama-Adaptive-Image-Code-Gen.

You can download this and use these commands to run and test this feature of create and generate images with ollama.

NOTE: Compose up process might upto 20 - 25 Mins. first time. Because it will download all the respective ModelFiles

Let's start:

git clone https://github.com/jaypatel15406/Ollama-Adaptive-Image-Code-Gen.git
Cloning into 'Ollama-Adaptive-Image-Code-Gen'...
Resolving deltas: 100% (30/30), done.

cd Ollama-Adaptive-Image-Code-Gen

Ollama-Adaptive-Image-Code-Gen>pip3 install -r requirements.txt
Collecting ollama (from -r requirements.txt (line 1))
...
Installing collected packages: propcache, multidict, frozenlist, aiohappyeyeballs, yarl, aiosignal, ollama, 
aiohttp
Successfully installed aiohappyeyeballs-2.4.8 aiohttp-3.11.13 aiosignal-1.3.2 frozenlist-1.5.0 multidict-6.1.0
ollama-0.4.7 propcache-0.3.0 yarl-1.18.3

Ollama-Adaptive-Image-Code-Gen>python main.py
 utility : pull_model_instance : Instansiating 'llama3.1' ...
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling manifest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 667b0c1932bc
 

Seams to work but I need more memory:

Ollama-Adaptive-Image-Code-Gen>python main.py
 utility : pull_model_instance : Instansiating 'llama3.1' ...
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling manifest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 667b0c1932bc
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 948af2743fc7
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 0ba8f0e314b4
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 56bb8bd477a5
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : pulling 455f34728c9b
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : verifying sha256 digest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : writing manifest
 utility : pull_model_instance : 'llama3.1' Model Fetching Status : success

=========================================================================================

 utility : get_prompt_response : Prompt : Choose the dimension of the shape: '2D' or '3D'. NOTE: Return only the chosen dimension.
ERROR:root: utility : get_prompt_response : Error : model requires more system memory (5.5 GiB) than is available (5.1 GiB) (status code: 500) ...