Integration of azure vector search with azure document intelligence

[Timothyhuiyukfai]

Great work with integrated data chunking and embedding.
Asking from a RAG context (complex documents, e.g. financial statement) , great work with integrated data chunking and embedding, how does the current framework works with the skills in document intelligence where you have to convert financial tables into json and feeds into LLM, given current framework is using chunk id as the key. Or team is expect this to resolve with prompt flow and sk or other methods? Any sample or best practise?

[mattgotteiner]

Hi @Timothyhuiyukfai

We have a demo that shows this but it's in python.
https://github.com/Azure-Samples/azure-search-openai-demo/

We can try to pull the functionality into the .NET demo, thanks for the feedback