How to build custom key-value extraction (similar to Azure Document Intelligence)?

Hi everyone, I’m trying to build a custom document understanding system and could use some guidance. Currently, I’m using Azure Document Intelligence, where we can define specific fields and train a model by annotating documents. The trained model then extracts only the required key-value pairs from new documents. I’m interested in building a similar solution using open-source models available on Hugging Face, but I’m not sure where to begin. Could anyone suggest: Suitable models or approaches for extracting specific fields from documents Recommended workflows for training such a system Thanks in advance for your help!