Save AI Tokens When Working With Multiple Screenshots

Description and use

Use Fuji OCR to locally extract text from screenshots, reducing token usage and enhancing privacy when working with AI assistants.

Problem

Sending many screenshots to an AI coding assistant increases visual input and token usage, even when only the text inside the images is needed.

Outcome

Local OCR reduces unnecessary image input, lowers token consumption, speeds up text extraction, and enhances privacy by avoiding external OCR services.

Workflow

• Capture the required screen area.
• Extract the text locally with Fuji OCR.
• Review the extracted text.
• Send only the relevant text to your AI assistant.

Evidence

Instead of sending every screenshot directly to the AI, you can first extract the text locally using Fuji OCR and then send only the relevant text.

Source