Markup is an online annotation tool designed to convert unstructured documents into structured formats suitable for Machine Learning (ML) and Natural Language Processing (NLP) tasks. This blog will guide you through the installation and usage of Markup, while also offering troubleshooting tips to ensure your experience is smooth and productive.

Key Features of Markup

• Predictive Annotation: Markup’s machine learning-powered feature recommends complex annotations as you work, making the annotation process quicker and more efficient.
• Integrated Ontology Access: Gain access to a variety of common ontologies (like UMLS and SNOMED-CT) and the ability to upload custom ontologies for enhanced concept mapping.
• Predictive Ontology Mapping: This feature uses machine learning to suggest suitable mappings to recognized terminologies based on the text you’re annotating.
• User-Friendly Interface: Markup is designed for all users, regardless of technical expertise, enabling everyone to begin annotating documents with ease.

Installation Steps

Here’s how you can set up Markup on your local machine:

1. Clone the repository and install dependencies:

git clone https://github.com/samueldobbi/markup
cd markup
yarn install

2. Install the Supabase CLI.
3. Start Supabase by running the command:

supabase start

This will output an API URL and anon key. Make sure to add both to the .env.local file.

4. For optional functionality, add an OpenAI API key to the .env.local file.
5. Run the development server using:

yarn start

6. Open Markup in your web browser by navigating to localhost:3000.

Understanding Markup’s Functionality Through Analogy

Imagine you are a librarian tasked with organizing a vast library of unstructured books. Every book represents unstructured data such as text documents and articles. Initially, the job seems overwhelming, but with an exceptional assistant (Markup), your task becomes manageable.

Markup acts like your assistant who not only helps you organize the books but also learns your preferences. When you begin to categorize books (annotating documents), it predicts which categories you might need next (predictive annotation) and even suggests related books you might have missed (predictive ontology mapping). As you continue to catalog more books, your assistant improves its suggestions, ensuring that your workflow remains efficient. Thus, your library transforms into a well-organized treasure trove of information, making it accessible and understandable for others.

Getting Started

To dive deeper into using Markup effectively, refer to the quick start guide for detailed instructions and tips.

Troubleshooting

If you run into any issues, here are some steps to help you out:

• Cannot Access Localhost: Ensure you have started the development server properly and check if there are any error messages in your terminal.
• Issues with API Keys: Verify that your .env.local file is correctly configured with the necessary API keys and restart the server after any changes.
• Dependency Errors: Ensure all dependencies are installed correctly. You can rerun yarn install to double-check.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.