https://github.com/davidmoserai/bachelor_thesis

Last synced: 22 Mar 2025

https://github.com/davidmoserai/azuredocumentintelligencechunker

A lightweight Python library for metadata-rich document chunking in Retrieval-Augmented Generation (RAG) workflows. It leverages Azure AI Document Intelligence to enhance chunking by retaining hierarchical structure, page numbers, and bounding boxes for seamless integration with PDF viewers.

agent agents azure azure-ai-document-intelligence azure-ai-search chunking document-chunking langchain layout-parser layout-parsing llm production-grade python rag react react-pdf-viewer retrieval-augmented-generation unstructured-data

Last synced: 08 Feb 2026