FYI jin.ai reader can now be self hosted #5789
Replies: 1 comment 2 replies
-
|
Unfortunately, image processing is not working for now. |
Beta Was this translation helpful? Give feedback.
-
|
Is it planned by any chance? Also do you know if it was part of the non opened part of jina reader or is most of the code is in their repo? |
Beta Was this translation helpful? Give feedback.
-
|
It cat take screenshots of the page but it does not extracts pictures from website. http://reader.berlin.cx/instant-screenshots/pageshot-2a302cbf-fd44-47d5-bdef-5b85aa3e5b5a.png Visit https://reader.berlin.cx/{any url} for markdown output or curl example from above to take screenshot/pageshot Demo is slow bc of sever specs CPU: 1 vCore, RAM: 0.5 GB |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
For those wondering, jin.ai reader is something that makes it extra easy to turn a URL into LLM friendly markdown output. Including base64 images etc.
Link : https://github.com/jina-ai/reader
Now, even though it was on GitHub, there were some key components missing that made it impossible to self-host until now.
Someone made a docker container for it, making it easy to self-host the whole thing. Here's the link: https://github.com/intergalacticalvariable/reader
Unfortunately, I'm not able to test it right now, but I thought it was worth mentioning here, because I think it would be a nice addition to an open WebUI Docker Compose setup with a simple tool to send URLs.
Beta Was this translation helpful? Give feedback.
All reactions