Enhancing your natural language processing (NLP) applications can feel like assembling a complex jigsaw puzzle. Every piece—like classifiers, extractors, and generators—needs to fit perfectly into your project to turn it into a cohesive masterpiece. This guide will help you navigate through the bricks of our open-source library, allowing you to add dynamic language features to your work effortlessly.

Why Bricks?

Imagine a construction site where every developer has a toolbox filled with ready-made bricks to craft beautiful structures. That’s essentially what our bricks library offers—an easy-to-use collection of natural language enrichments that you can integrate directly into your projects. It’s not about installing it with a simple command but about copy-pasting code snippets that allow you to elevate your text-processing capabilities.

Demo

Curious to see bricks in action? Check out our demo video by clicking the image below or follow this link.

What are Classifiers, Extractors, and Generators?

Think of modules as different departments in a library:

• Classifiers: Like librarians who classify books into genres, classifiers summarize text into categories such as news or blog posts.
• Extractors: The diligent assistants who retrieve specific information, like finding an author’s name in a sea of pages.
• Generators: Creative writers who generate new stories or interpret content in different languages.

Structure of Modules

Every module comes as a neatly organized package:

• __init__.py: The key entry point for executing the module.
• README.md: Holds a description visible on the platform’s detail page.
• code_snippet_refinery.md: Displays a code snippet tailored for SpaCy inputs.
• code_snippet_common.md: A general code snippet suitable for any Python environment.
• config.py: A synchronization script between the repository and our online platform.

If you are interested in contributing a new module, please review our contributing guidelines.

Getting Started

You can access all the exciting modules at bricks. To host them locally, follow these steps:

1. Clone the repository.
2. (Optional) Create a virtual environment.
3. Install the dependencies:

pip install -r requirements.txt

4. Run the FastAPI server:

uvicorn api:api

5. Open your browser and go to http://localhost:8000/docs to see the documentation.

Contributing

We continuously add modules to this library for broader usability. If you wish to contribute your module, refer to the contributing guidelines, and pop into our Discord for any questions you might have.

If our repository has helped you out, drop us a star! And don’t forget to check out refinery.

Refinery

Explore our primary project, refinery, designed to help you scale, assess, and maintain your training data. The modules from bricks can be utilized immediately in refinery.

Regular Updates and Newsletter

We actively enrich bricks with new modules and aim to release two or more each week. Stay informed by subscribing to our newsletter.

License

This repository is licensed under the Apache License, Version 2.0. You can view a copy of the License file.

Troubleshooting

While things usually run smoothly, sometimes you might hit a snag. Here are some ideas for troubleshooting:

• Ensure all prerequisites are installed before running the application.
• Double-check URLs and paths if you’re cloning the repository.
• If you experience issues with dependencies, consider reinstalling them.

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.