llama_index icon indicating copy to clipboard operation
llama_index copied to clipboard

Google Scholar/ArXiv connectors

Open taesiri opened this issue 2 years ago • 1 comments

Hello and thanks for this amazing project.

I was wondering about the possibility of adding support for building an index out of Google Scholar and/or ArXiv search results. All the individual parts seem easy, but we don't have an easy way for that (obtaining the papers from the results => extracting the text from a PDF => creating the index). I am not sure about the general interest, but this can be very useful when searching for papers or doing a literature review.

Thanks

taesiri avatar Feb 09 '23 02:02 taesiri

There exits an ArXiv API example here:

https://github.com/emptycrown/llama-hub/tree/main/loader_hub/papers/arxiv

ifrit98 avatar Feb 10 '23 18:02 ifrit98

@ifrit98 Awesome! Thanks for the link.

taesiri avatar Feb 10 '23 18:02 taesiri

yep hope that works @taesiri! - will close this issue unless there's anything else

jerryjliu avatar Feb 10 '23 18:02 jerryjliu