#Document Processing

ExtractThinker is a flexible library for seamless data extraction using advanced LLM technology. It features ORM-style interaction between files and LLMs and supports multiple document loaders like Tesseract OCR and Azure Form Recognizer. Users can customize document extraction with contract definitions and utilize asynchronous processing for efficiency. Suitable for Intelligent Document Processing, it offers tools for document splitting, classification, and processing, with a structure aligned with the LangChain ecosystem. Begin using ExtractThinker by installing it via pip to enhance document management.

The i-Code project develops integrative and composable AI technologies aimed at advancing multimodal learning across datasets like vision, language, and speech. It includes i-Code V1 for foundational multimodal models, i-Code V2 for autoregressive generation, i-Code V3 for any-to-any diffusion, and i-Code Studio for configurable AI frameworks. The project further strengthens document intelligence via i-Code Doc and facilitates knowledge-based visual question answering with MM-Reasoner, encouraging contributions under the Microsoft open-source code of conduct.