YESSSSSSSSSSSSSSS

.github/workflows/pypi_release.yml

@@ -0,0 +1,34 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+     - '*'
+
+jobs:
+  build-n-publish:
+    name: Build and publish to PyPI
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@master
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.12'
+    - name: Install pypa/setuptools
+      run: >-
+        python -m
+        pip install wheel
+    - name: Extract tag name
+      id: tag
+      run: echo ::set-output name=TAG_NAME::$(echo $GITHUB_REF | cut -d / -f 3)
+    - name: Update version in setup.py
+      run: >-
+        sed -i "s/{{VERSION_PLACEHOLDER}}/${{ steps.tag.outputs.TAG_NAME }}/g" setup.py
+    - name: Build a binary wheel
+      run: >-
+        python setup.py sdist bdist_wheel
+    - name: Publish distribution to PyPI
+      uses: pypa/gh-action-pypi-publish@master
+      with:
+        password: ${{ secrets.PYPI_API_TOKEN }}

README.md

@@ -0,0 +1,71 @@
+# SpiceJack
+
+SpiceJack is a tool for generating json questions and answers from documents in python.
+
+## Usage
+
+```python
+from spicejack.pdf import PDFprocessor
+
+def filter1(list):
+    """
+    Example filter
+    """
+    return [i.replace("badword","b*dword") for i in list]
+
+
+processor = PDFprocessor(
+    "/path/to/Tax_Evasion_Tutorial.pdf",
+    use_legitimate = True, # Runs the processor with the openai api (See "legitimate use")
+    filters = (filter1,) # Extra custom filters
+)
+
+processor.run(
+    thread = True # Runs the processor in a child thread. (threading.Thread)
+    process = True # Runs the processor in a child thread. (multiprocessing.Process)
+    logging = True # Prints the responses from the LLM
+)
+
+```
+
+## Legitimate use
+
+Create a file named .env and put this:
+
+```dotenv
+OPENAI_API_KEY = "<YOUR-OPENAI-API-KEY>"
+```
+
+## Installation
+
+```bash
+pip install spicejack
+```
+
+## Support me
+
+You can use SpiceJack for completely free, but donations are very appreciated as I am making this on an 10+ year old laptop.
+
+### Bitcoin
+
+bc1q7xaxer2xpxttm3vpzc8s9dutvck8u9ercxxc95
+
+### Ethereum
+
+0xB7351e098c80E2dCDE48BB769ac14c599E32c47E
+
+### Monero
+
+44Y47Sf2huJV4hx7K1JrTeKbgkPsWdRWSbEiAHRWKroaGYAnxkPjdxhUsDeiFeQ3wc6Tw8v3uYTZMbBUfcdUUgqt5HCqbtY
+
+### Litecoin
+
+LQzd9phuN7iPRn8p5rT1zyVssJ8nY5WjM5
+
+## Roadmap
+
+- [x] Python library
+
+- [ ] Mass generation
+
+- [ ] GUI

setup.py

@@ -0,0 +1,35 @@
+from setuptools import setup, find_packages
+import codecs
+import os
+
+here = os.path.abspath(os.path.dirname(__file__))
+
+with codecs.open(os.path.join(here, "README.md"), encoding="utf-8") as fh:
+    long_description = "\n" + fh.read()
+
+VERSION = '{{VERSION_PLACEHOLDER}}'
+DESCRIPTION = 'Python package for generating training data from documents.'
+
+# Setting up
+setup(
+    name="vidstream",
+    version=VERSION,
+    author="LIZARD-OFFICIAL-77",
+    author_email="<lizard.official.77@gmail.com>",
+    description=DESCRIPTION,
+    long_description_content_type="text/markdown",
+    long_description=long_description,
+    packages=find_packages(),
+    install_requires=(
+        "g4f",
+        "pdfminer.six",
+        "python-dotenv"
+    ),
+    keywords=['python', 'json', 'stream', 'video stream', 'camera stream', 'sockets'],
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+        "Programming Language :: Python :: 3",
+        "Operating System :: POSIX :: Linux",
+    ]
+)