Docktype:pdf ^new^ Jun 2026
: Ensure there is no white space or any characters before the or tags, as this can cause parsing errors in many PDF rendering engines.
The PDF is the universal standard for "fixed" content. Unlike a webpage that might change its layout based on your screen size, a PDF preserves the exact formatting intended by the author, making it the preferred format for official documentation. docktype:pdf
Upload PDF → OCR (if needed) → Chunk text → AI Q&A → Export JSON : Ensure there is no white space or
: For this specific library, the recommended DOCTYPE is slightly different: . Upload PDF → OCR (if needed) → Chunk
By explicitly labeling the document type in the metadata, archivists ensure that even if the file extension is lost, the system knows how to handle the data. 3. Why the Distinction Matters