Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API (github.com)

Ocrbase has launched a robust OCR (Optical Character Recognition) document processing and structured data extraction API built with modern TypeScript technologies. The platform uses PaddleOCR for accurate text extraction while leveraging AI-powered LLMs (Large Language Models) for structured data pulling, enabling users to define custom schemas for targeted extraction. It supports real-time job tracking via WebSocket and offers a RESTful API with comprehensive OpenAPI documentation, along with a type-safe TypeScript SDK that integrates seamlessly with React applications. This announcement is significant for the AI/ML community as it combines the power of OCR technology with advanced data extraction capabilities, streamlining workflows for developers and businesses that handle large volumes of documents. The use of technologies such as PostgreSQL, Redis, and Docker enhances the scalability and reliability of the service. Furthermore, the API's real-time job status updates and support for custom schema generation offer practical utilities for developers looking to optimize document management processes. Ocrbase positions itself as a go-to solution for organizations aiming to improve their data extraction workflows through modern APIs.