📄 Multi-modal Document Preprocessing with Azure Document Intelligence

✨ Features

1. 📝 Generate a document parsed results using Document Intelligence, and output it in Markdown format. > output
2. 🖼️ Extract figures from documents and save them as PNG images. > output
3. 🤖 Generate figure descriptions using Azure OpenAI Multimodal.
4. 📝 Update markdown outputs with generated descriptions. > output
5. 📊 Extract tables and convert them into Excel files. > output
6. 📖 Text Chunking to markdown ouputs using MarkdownHeaderTextSplitter, RecursiveContentChunker, and SemanticContentChunker (TBD) > markdown chuck output | recursive chunk output

🚀 Usage

python doc_intelli_workflow.py

📚 Learn More

• 📘 Document Intelligence Official Samples: Python (v4.0) / RAG samples / Figure understanding.
• Build Intelligent RAG for Multimodality and Complex Document Structures
• nohanaga: Document Intelligence Samples | 🔗 Output: Article in Japanese
• 📖 7 Chunking Strategies for Langchain
• MarkdownHeaderTextSplitter
• ⚡ Azure Functions vs. Indexers: AI Data Ingestion
• RAG Time: Mastering RAG