ai/vision

Computer vision skill for analyzing images and extracting text using state-of-the-art models.

Features

• Object Detection: Identify objects and their bounding boxes.
• OCR: Extract text from images with high accuracy.
• Image Captioning: Generate descriptive captions for images.

Installation

spm install ai/vision

Usage

import { VisionAgent } from "ai/vision";

const agent = new VisionAgent({ apiKey: process.env.VISION_API_KEY });

const result = await agent.analyzeImage("./receipt.jpg", {
  features: ["OCR", "DOCUMENT_TEXT_DETECTION"]
});

console.log(result.text);