ai-article-generator 0.1.7

A Python library for generating articles using AI.

ai_article_generator

A Python library for generating articles using AI. This library provides tools and utilities to automate the creation of articles, leveraging machine learning and natural language processing techniques.

Installation

Install the library from PyPI:

pip install ai-article-generator

Or, for development, clone the repository and install dependencies:

pip install -r requirements.txt

API Key Setup

You must create a .env file in your project directory with your OpenAI API key:

OPENAI_API_KEY=your-openai-api-key-here

This is required for the library to access the OpenAI API.

Usage

Import and use the library in your Python code:

from ai_article_generator.generator import ArticleGenerator

Example Usage

from ai_article_generator.generator import ArticleGenerator

# Example instructions for article sections
instructions = {
    "Article Header": {
        "instructions": "Write a header for a tech article about AI in journalism.",
        "response_format": {"title": "Article Main Title", "subtitle": "Catchy Subtitle"},
        "html_template": "<h1>{title}: {subtitle}</h1>",
    },
    "SEO Data": {
        "instructions": "Generate an SEO title (around 60 characters) and meta description (around 155 characters) for an article about AI in journalism.",
        "response_format": {
            "seo_title": "SEO Optimized Title",
            "meta_description": "Compelling meta description for search engines",
        },
        # No html_template here, so it will return the structured data as a dictionary
    },
    "Article Image": {
        "content_type": "image", # Specify content type as image
        "instructions": "A vibrant illustration of a futuristic city with flying cars and holographic billboards, in a synthwave art style.", # This is the image prompt
        # For image sections, response_format is mainly for clarity; the actual data passed to html_template is {"image_url": ...}
        "response_format": {"image_url": "URL of the AI-generated image"},
        "html_template": "<figure>\n  <img src='{image_url}' alt='AI-generated image for the article' style='max-width:100%; height:auto;' />\n  <figcaption style='text-align:center; font-style:italic; color:#555;'>A vivid, AI-generated illustration.</figcaption>\n</figure>",
        # Optional: specify DALL·E model, size, quality for the image
        # "image_model": "dall-e-3",
        # "image_size": "1024x1024", # Or other DALL·E supported sizes like "1792x1024", "1024x1792"
        # "image_quality": "standard" # or "hd" for DALL·E 3
    }
}

# Any additional data your sections might need
additional_data = {"keywords": ["AI", "journalism", "technology"]}

# Create the generator (article_type can be 'review', 'news', 'guide', 'feature', or 'generic')
generator = ArticleGenerator(
    instructions=instructions,
    additional_data=additional_data
)

# Generate the article sections as HTML
try:
    generated_outputs = generator.generate() # Output can be HTML or structured data
    for section_name, output_content in generated_outputs.items():
        print(f"Section: {section_name}")
        if isinstance(output_content, str): # HTML content
            print(f"HTML Output:\\n{output_content}\\n")
        elif isinstance(output_content, dict): # Structured data (e.g., SEO)
            print("Structured Data Output:")
            for key, value in output_content.items():
                print(f"  {key}: {value}")
            print("\\n")
        # Image sections also return HTML strings, they are handled by the isinstance(str) check above
except Exception as e:
    print(f"Error generating article: {e}")

Arguments and Options

The ArticleGenerator class accepts the following arguments:

Argument	Required?	Default	Description
instructions	Yes	—	Section instructions (dict)
additional_data	Yes	—	Extra data for sections (dict)
article_type	No	"generic"	Type of article (affects system prompt)
system_prompt	No	None	Custom system prompt
model	No	"gpt-4o-mini"	OpenAI model to use

Example with optional fields

generator = ArticleGenerator(
    instructions=instructions,
    additional_data=additional_data,
    article_type="feature",      # optional
    system_prompt=None,          # optional
    model="gpt-4o-mini"          # optional
)