llama-ocr-cli
v1.0.0
Published
CLI tool for OCR using llama-ocr
Downloads
25
Readme
llama-ocr-cli
A command-line interface for performing OCR on images using llama-ocr.
Installation
npm install -g llama-ocr-cli
Prerequisites
You need a Together AI API key to use this tool. You can either:
- Set it as an environment variable:
TOGETHER_API_KEY=your-key-here
- Pass it as a command line argument:
--api-key your-key-here
Usage
Basic usage:
llama-ocr image.jpg
With explicit API key:
llama-ocr image.jpg --api-key your-key-here
Save output to file:
llama-ocr image.jpg -o output.md
Options
-k, --api-key <key>
: Together AI API key (overrides environment variable)-o, --output <file>
: Output file for the extracted text (defaults to stdout)-V, --version
: Output the version number-h, --help
: Display help information
Development
- Clone the repository
- Install dependencies:
npm install
- Build the project:
npm run build
- Run in development mode:
npm run dev
Publishing
This package is automatically published to npm when a new GitHub release is created. The GitHub Action workflow will:
- Build the package
- Publish to npm registry
To publish a new version:
- Update version in package.json
- Create a new release on GitHub
- The GitHub Action will automatically publish to npm
License
MIT