Releases

Initial Release

Initial Release

Deployed: December 31, 2024

Our initial release introduces a comprehensive platform for data extraction and processing, focusing on robust document handling and schema management capabilities.

Core platform

  • Launch of the core platform with foundational data processing capabilities
  • Release of DeepExtract basic version, providing essential extraction features for common document formats
  • Implementation of Probabilistic JSON schemas for flexible data modeling

Document processing

  • Initial PDF processing pipeline with basic OCR capabilities
  • Standard document format support including PDFs, DOC, DOCX, and TXT files
  • Fundamental extraction capabilities for text-based content

Integration features

  • Schema and Prompt combinations enabling customizable transformations
  • Basic integration API endpoints for automated processing
  • Initial set of pre-configured extraction templates

User interface

  • Core dashboard functionality for document management
  • Basic document processing status monitoring
  • Simple visualization of extraction results

This release establishes the foundation for our document processing platform, offering essential tools for data extraction and transformation while maintaining high accuracy and reliability.