The problem
Maxun has a feature where users can upload a document and get back its content as text, HTML, or a list of links (soon also a summary and AI-based structured extraction). Right now this only works for PDFs, if you try to upload a Word document (.docx), it gets rejected outright since the system only lets PDFs through.
A lot of the documents people actually want data from aren't PDFs though reports, letters, and contracts are often just Word docs.
What needs to change
Add DOCX as a supported upload type and extract its text/HTML content, the same way PDFs are handled today.
What "done" looks like
A user uploads a .docx file instead of a PDF.
The system reads it and returns the content in the same output formats already supported for PDFs (markdown/html/links, plus extraction).
The problem
Maxun has a feature where users can upload a document and get back its content as text, HTML, or a list of links (soon also a summary and AI-based structured extraction). Right now this only works for PDFs, if you try to upload a Word document (.docx), it gets rejected outright since the system only lets PDFs through.
A lot of the documents people actually want data from aren't PDFs though reports, letters, and contracts are often just Word docs.
What needs to change
Add DOCX as a supported upload type and extract its text/HTML content, the same way PDFs are handled today.
What "done" looks like
A user uploads a .docx file instead of a PDF.
The system reads it and returns the content in the same output formats already supported for PDFs (markdown/html/links, plus extraction).