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.
react python agent azure chunking agents unstructured-data rag production-grade react-pdf-viewer layout-parser llm langchain retrieval-augmented-generation azure-ai-search azure-ai-document-intelligence layout-parsing document-chunking
- Updated
Jan 11, 2025 - Python