View only. Sign in to run this demo. You can also run it with your own model key, without an account.
Parser
Read text and layout from PDF, Word files, and images accurately
How to use the Parser
- 1Add a documentUpload a PDF, Word file or image, or start from a ready-made document.
- 2Choose the parserEach parser reads in its own way. Pick one that fits the document, then read it.
- 3Explore the outputSee it rendered, as markdown or as plain text. Search it, jump by outline, copy or download it.
- 4Compare parsersRead the same document with another parser and compare the two outputs side by side.
- Vision and Vision+ read at most 10 pages. Multimodal reads PDF files only.
- Nothing is saved: the document and its parsed output stay in this session.
Start from a ready-made document
The document and the parser
Upload a file, choose how it is read, and read it. Reading it again with another parser adds a second output to compare.
This parser is good for fast, high-quality parsing of PDFs with headings and tables. It uses the GPU-accelerated Docling service hosted by Haaga-Helia and returns markdown with metadata.
No parsed output yet
Upload a document and click Read document. The output appears here next to the original, with search, outline and downloads.
