Image Insight is a Chrome extension that allows users to extract text from images and generate detailed descriptions using OCRSpace service and Pixtral 12B model from Mistral.
- Image Upload: Easily upload images through file selection or drag-and-drop.
- Clipboard Paste: Quickly paste images directly from your clipboard.
- Text Extraction: Extract text from images using OCR technology.
- Image Description: Generate detailed descriptions of images using AI.
- Dark Mode: Toggle between light and dark themes for comfortable viewing.
- Download & Copy: Save extracted text or copy it to your clipboard with ease.
- API Integration: Utilizes OCRSpace for text extraction and Mistral AI for image description.
- Clone this repository or download the ZIP file.
- Open Chrome and navigate to
chrome://extensions/. - Enable "Developer mode" in the top right corner.
- Click "Load unpacked" and select the directory containing the extension files.
- Click on the Image Insight icon in your Chrome toolbar.
- Upload an image using the "Upload Image" button or paste from clipboard.
- Click "Extract" to extract text from the image or "Describe" to generate a description.
- View the results in the text area below.
- Use the "Download" or "Copy" buttons to save or copy the output.
Before using the extension, you need to set up your API keys:
- Click the "Settings" button in the extension popup.
- Enter your OCRSpace API key and Mistral API key in the respective fields. a) OCRSpace API = https://ocr.space/OCRAPI b) Mistral API = https://console.mistral.ai/
- Click "Save" for each API key.
The extension is built using HTML, CSS (with Tailwind), and JavaScript. Key files include:
popup.html: Main extension interfacepopup.js: Core functionality for the extensionoptions.js: Handles settings and API key managementstyles.css: Custom styles on top of Tailwind CSS
Contributions are welcome! Please feel free to submit a Pull Request.
This project is open source and available under the MIT License.
- OCRSpace for text extraction API
- Mistral AI for image description API
- Tailwind CSS for styling
