Hi Phidata community! 
I’m working with Docx Knowledge Base and I want to know what would be the best strategy for fetch very specific sections (e.g., “get section 3 from doc_1”).
What’s the best combination of vector DB, chunking strategy, and embedder for this kind of precise retrieval? Is possible to use Chroma with IDs for each document?
Thanks for any tips!
Hi @Southern_Push2935
Thank you for reaching out and using Phidata! I’ve tagged the relevant engineers to assist you with your query. We aim to respond within 24 hours.
If this is urgent, please feel free to let us know, and we’ll do our best to prioritize it.
Thanks for your patience!
@Southern_Push2935 To check for the the best combination, you must play around with the settings and see what gives you the best result. As for your example of “get sections 3 from doc_1” I am unsure if a knowledge base could do that for you. But I look forward to hearing from you if it worked or not