Groq CLI Extractor

This is a lightweight memory-safe information and context extraction tool powered by Groq's inference engine. It streams local images and PDFs, converts them into natively-encoded Base64 without crashing the V8 heap, and extracts their data using Groq's Vision API.

🚀 Installation

Install the package globally via NPM:

npm install -g groq-cli-extractor

##⚙️ Configuration

##  Windows(PowerShell)
$env:GROQ_API_KEY="gsk_your_api_key_here"

## macOS/Linux
export GROQ_API_KEY="gsk_your_api_key_here"

## 🛠️ Usage
Once installed and configured, you can extract data from any file (under 5MB) directly from your terminal:
groq-extract /path/to/your/image.png

## ⚠️ Important Note: Upstream Model Lifecycle
This CLI currently relies on Groq's Vision models (e.g., meta-llama/llama-4-scout-17b-16e-instruct).

Groq frequently updates, deprecates, and decommissions their preview models. If the tool suddenly begins throwing API errors in the future, it is highly likely the targeted model has been decommissioned by Groq.

If this happens, you will need to update the model string in the source code to Groq's latest supported Vision model and reinstall the package. Check the Groq Model Documentation for the most up-to-date model IDs.