PDF — {pdf_meta.get('pages', '?')} pages
{pdf_text[:5000]} ",
"raw_length": size,
"extension": ext,
"is_markdown": False,
"is_pdf": True,
"unsupported": False,
"pdf_metadata": pdf_meta,
"pdf_toc": pdf_toc,
"size_bytes": size,
}
except Exception as e:
logger.error(f"PDF read error for {path}: {e}")
raise HTTPException(status_code=500, detail=f"Error reading PDF: {e!s}")
# === Images: return as viewable image ===
if is_image(ext):
size = file_path.stat().st_size
mime = media_mime_type(str(file_path))
# #108-B1 — the raw endpoint returns JSON (FileRawResponse), so the
# standalone