Merge branch 'main' into feature/support-markdown

.dockerignore

@@ -0,0 +1,18 @@
+.git
+.gitignore
+.github
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env/
+venv/
+.env
+*.log
+.pytest_cache/
+.coverage
+htmlcov/
+dist/
+build/
+*.egg-info/

.github/workflows/docker-publish.yml

@@ -0,0 +1,90 @@
+name: Docker
+
+on:
+  push:
+    branches: [ "main" ]
+    tags: [ 'v*.*.*' ]
+    paths:
+      - 'podcastfy/**'
+      - 'setup.py'
+      - 'requirements.txt'
+      - 'Dockerfile'
+      - 'Dockerfile.dev'
+      - '.github/workflows/docker-publish.yml'
+  pull_request:
+    branches: [ "main" ]
+    paths:
+      - 'podcastfy/**'
+      - 'setup.py'
+      - 'requirements.txt'
+      - 'Dockerfile'
+      - 'Dockerfile.dev'
+      - '.github/workflows/docker-publish.yml'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.CR_PAT }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      # Build and push PyPI version with caching
+      - name: Build and push PyPI Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: Dockerfile
+          push: true
+          tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:latest
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha,scope=prod
+          cache-to: type=gha,scope=prod,mode=max
+
+      # Build and push development version with caching
+      - name: Build and push development Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: Dockerfile.dev
+          push: true
+          tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:dev
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha,scope=dev
+          cache-to: type=gha,scope=dev,mode=max
+
+      - name: Test Docker images
+        env:
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        run: |
+          # Test PyPI version
+          docker pull ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:latest
+          docker run --rm ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:latest python3 -c "import podcastfy"
+          
+          # Test development version
+          docker pull ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:dev
+          docker run --rm ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:dev python3 -c "import podcastfy"

.github/workflows/python-app.yml

@@ -18,10 +18,8 @@ on:
       - 'setup.py'
       - '.github/workflows/**'
       - 'pyproject.toml'
-
 permissions:
   contents: read
-
 jobs:
   build:
     runs-on: ubuntu-latest
@@ -51,7 +49,7 @@ jobs:
       run: |
         set -e
         . /opt/venv/bin/activate
-        pip install flake8 pytest
+        pip install flake8 pytest pytest-xdist
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Check versions and list packages
       run: |
@@ -80,7 +78,7 @@ jobs:
       run: |
         set -e
         . /opt/venv/bin/activate
-        pytest
+        pytest -n auto --dist loadfile
     - name: Upload test artifacts
       uses: actions/upload-artifact@v3
       with:

Dockerfile

@@ -0,0 +1,37 @@
+# Use Ubuntu 24.04 as base image
+FROM ubuntu:24.04
+
+# Prevent interactive prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install system dependencies
+RUN apt-get update && \
+    apt-get install -y \
+    python3-full \
+    python3-pip \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create and activate virtual environment
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Upgrade pip
+RUN python3 -m pip install --upgrade pip
+
+# Install podcastfy from PyPI
+RUN pip install --no-cache-dir podcastfy
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+
+# Verify installations
+RUN echo "Verifying installations:" && \
+    echo "Ubuntu version:" && cat /etc/os-release && \
+    echo "FFmpeg version:" && ffmpeg -version && \
+    echo "Python version:" && python3 --version && \
+    echo "Pip version:" && pip --version && \
+    echo "Installed packages:" && pip list
+
+# Command to run when container starts
+CMD ["python3"]

Dockerfile.dev

@@ -0,0 +1,60 @@
+# Use Ubuntu 24.04 as base image to match CI environment
+FROM ubuntu:24.04
+
+# Prevent interactive prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies matching CI configuration
+RUN apt-get update && \
+    apt-get install -y \
+    python3-full \
+    python3-pip \
+    python3-venv \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create and activate virtual environment
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Upgrade pip
+RUN python3 -m pip install --upgrade pip
+
+# Install testing and linting dependencies
+RUN pip install --no-cache-dir \
+    flake8 \
+    pytest \
+    pytest-xdist
+
+# Copy requirements first to leverage Docker cache
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the package files
+COPY . .
+
+# Install the package in editable mode
+RUN pip install -e .
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+
+# Verify installations
+RUN echo "Verifying installations:" && \
+    echo "Ubuntu version:" && cat /etc/os-release && \
+    echo "FFmpeg version:" && ffmpeg -version && \
+    echo "Python version:" && python3 --version && \
+    echo "Pip version:" && pip --version && \
+    echo "Installed packages:" && pip list
+
+# Run flake8 checks during build
+RUN flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics && \
+    flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+# Command to run when container starts
+CMD ["python3"]

Makefile

@@ -4,7 +4,7 @@ lint:
 	mypy podcastfy/*.py
 
 test:
-	python3 -m pytest tests
+	poetry run pytest -n auto
 
 doc-gen:
 	sphinx-apidoc -f -o ./docs/source ./podcastfy

NOTICE

@@ -0,0 +1,7 @@
+Podcastfy
+Copyright 2024 Tharsis T. P. Souza
+------------------------
+This product includes software developed by:
+Tharsis T. P. Souza (www.souzatharsis.com) and all of the great contributors listed at https://github.com/souzatharsis/podcastfy/graphs/contributors.
+------------------------
+The text of the Apache License, Version 2.0 can be found in the LICENSE file.

README.md

@@ -6,8 +6,9 @@
 [![Downloads](https://pepy.tech/badge/podcastfy)](https://pepy.tech/project/podcastfy)
 [![Issues](https://img.shields.io/github/issues-raw/souzatharsis/podcastfy)](https://github.com/souzatharsis/podcastfy/issues)
 [![Pytest](https://github.com/souzatharsis/podcastfy/actions/workflows/python-app.yml/badge.svg)](https://github.com/souzatharsis/podcastfy/actions/workflows/python-app.yml)
+[![Docker](https://github.com/souzatharsis/podcastfy/actions/workflows/docker-publish.yml/badge.svg)](https://github.com/souzatharsis/podcastfy/actions/workflows/docker-publish.yml)
 [![Documentation Status](https://readthedocs.org/projects/podcastfy/badge/?version=latest)](https://podcastfy.readthedocs.io/en/latest/?badge=latest)
-[![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc-sa/4.0/)
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 ![GitHub Repo stars](https://img.shields.io/github/stars/souzatharsis/podcastfy)
 
 
@@ -17,7 +18,7 @@ https://github.com/user-attachments/assets/f1559e70-9cf9-4576-b48b-87e7dad1dd0b
 
 Podcastfy is an open-source Python package that transforms multi-modal content (text, images) into engaging, multi-lingual audio conversations using GenAI. Input content include websites, PDFs, YouTube videos, images, and Markdown files.
 
-Unlike UI-based tools focused primarily on note-taking or research synthesis (e.g. NotebookLM ❤️), Podcastfy focuses on the programmatic and bespoke generation of engaging, conversational transcripts and audio from a multitude of multi-modal sources enabling customization and scale.
+Unlike UI-based tools focused primarily on note-taking or research synthesis (e.g. NotebookLM ❤️), Podcastfy focuses on the programmatic and bespoke generation of engaging, conversational transcripts and audio from a multitude of multi-modal sources, enabling customization and scale.
 
 [![Star History Chart](https://api.star-history.com/svg?repos=souzatharsis/podcastfy&type=Date&theme=dark)](https://api.star-history.com/svg?repos=souzatharsis/podcastfy&type=Date&theme=dark)
 
@@ -102,17 +103,23 @@ python -m podcastfy.client --url <url1> --url <url2>
 
 - [CLI](usage/cli.md)
 
+- [Docker Image](usage/docker.md)
+
 - [How to](usage/how-to.md)
 
 Experience Podcastfy with our [HuggingFace](https://huggingface.co/spaces/thatupiso/Podcastfy.ai_demo) 🤗 Spaces app for a simple URL-to-Audio demo. (Note: This UI app is less extensively tested and capable than the Python package.)
 
 ## Customization 🔧
 
 Podcastfy offers a range of customization options to tailor your AI-generated podcasts:
-- Customize podcast [Conversation](usage/conversation_custom.md) (e.g. format, style, voices)
+- Customize podcast [conversation](usage/conversation_custom.md) (e.g. format, style, voices)
 - Choose to run [Local LLMs](usage/local_llm.md) (156+ HuggingFace models)
 - Set [System Settings](usage/config_custom.md) (e.g. output directory settings)
 
+## License
+
+This software is licensed under [Apache 2.0](LICENSE). [Here](usage/license-guide.md) are a few instructions if you would like to use podcastfy in your software.
+
 ## Contributing 🤝
 
 We welcome contributions! See [Guidelines](GUIDELINES.md) for more details.