Problem Description
https://github.com/opendataloader-project/opendataloader-pdf
This is the new SOTA pdf parser, we should look into adding support for these type of parsers, is anyone in team working on this?
or should I open a pull request for this?
Proposed Solution
We can likely improve accuracy of RAG based pipelines if we use opendataloader-pdf type of repos.
Alternatives Considered
No response
Additional Context
No response
Would you like to work on this?
Problem Description
https://github.com/opendataloader-project/opendataloader-pdf
This is the new SOTA pdf parser, we should look into adding support for these type of parsers, is anyone in team working on this?
or should I open a pull request for this?
Proposed Solution
We can likely improve accuracy of RAG based pipelines if we use opendataloader-pdf type of repos.
Alternatives Considered
No response
Additional Context
No response
Would you like to work on this?