[Enhancement]: Add MarkItDown support as OCR #8667
jkuehn
started this conversation in
Feature Requests & Suggestions
Replies: 1 comment
-
Some optimizations coming for file support that will generally help and only necessitate OCR when explicitly needed (in pdf/image context). |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
What features would you like to see added?
Microsoft MarkItDown is fairly new, but it works quite well and easily as OCR: https://github.com/microsoft/markitdown
It would be great to have it as an OCR option in LibreChat. An MCP server is available. Maybe the OCR feature can delegate to a MCP server tool?
More details
Currently Mistral OCR is the only option. It works well, but is not suitable for all corporate installations because of regulatory reasons.
Which components are impacted by your request?
No response
Pictures
No response
Code of Conduct
Beta Was this translation helpful? Give feedback.
All reactions