xfyun-ocr

Recognize text from images using iFlytek's Spark-based OCR LLM engine (通用文档识别/OCR大模型). Supports complex layouts including formulas, tables, columns, watermarks, and more.

Setup

1. Create an app at 讯飞控制台 with 通用文档识别 (OCR大模型) service enabled
2. Set environment variables:

   export XFYUN_APP_ID="your_app_id"
   export XFYUN_API_KEY="your_api_key"
   export XFYUN_API_SECRET="your_api_secret"
   

Usage

Basic OCR