Gemini File Search does not preserve document structure during OCR and text extraction—markdown headings are converted to plain text separated by newlines, losing the document hierarchy that is important for RAG retrieval quality.
factualpending
Evidence Quote
“you're not getting markdown headings with the OCR or with the text extraction. So here I have a heading one and a heading two. And if you look over here, it's just text separated by new lines. So you are losing the document hierarchy with this system.”
Created: 8/13/2026, 4:54:45 AM
My Notes
Loading notes...