Official documentation for Vectorcache - AI-powered semantic caching for LLM applications.
Visit the live documentation: docs.vectorcache.com
- Getting Started - Quick start guide, installation, and configuration
- SDK Documentation - JavaScript/TypeScript, Python, and cURL examples
- API Reference - Complete API documentation
- Guides - Best practices, similarity tuning, cost optimization, and security
- FAQ & Support - Common questions and support resources
- Python 3.8+
- pip
- Clone the repository:
git clone https://github.com/YOUR_USERNAME/vectorcache-docs.git
cd vectorcache-docs- Install dependencies:
pip install mkdocs-material
pip install mkdocs-git-revision-date-localized-plugin- Run local server:
mkdocs serve- Open http://localhost:8000 in your browser
Build static site:
mkdocs buildOutput will be in site/ directory.
We welcome contributions! Here's how:
- Fork the repository
- Create a feature branch:
git checkout -b feature/your-feature - Make your changes
- Test locally:
mkdocs serve - Commit:
git commit -m "Add your feature" - Push:
git push origin feature/your-feature - Open a Pull Request
docs/
├── index.md # Home page
├── getting-started/ # Quick start, installation, config
├── sdk/ # SDK documentation
├── api/ # API reference
├── guides/ # Best practices and guides
└── about/ # FAQ, pricing, support
Documentation is automatically deployed to GitHub Pages on push to main branch.
GitHub Actions workflow:
- Builds the docs with MkDocs Material
- Deploys to
gh-pagesbranch - Available at your GitHub Pages URL
This documentation is licensed under MIT License.
- Documentation Issues: GitHub Issues
- Product Support: support@vectorcache.com
- Discord: Join our community