Weixin-Liang / LLM-scientific-feedback

Can large language models provide useful feedback on research papers? A large-scale empirical analysis.
Creative Commons Attribution 4.0 International
489 stars 49 forks source link

Failed to parse XML... Error: not well-formed (invalid token): line 1, column 0 #10

Closed liuliAI closed 10 months ago

liuliAI commented 11 months ago

Failed to parse XML... Error: not well-formed (invalid token): line 1, column 0 Running on local URL: http://127.0.0.1:7860 Parsing PDF... Parsing XML...

Zhong-Zhang commented 11 months ago

Try this: https://github.com/Weixin-Liang/LLM-scientific-feedback/issues/6#issuecomment-1751886948

liuliAI commented 11 months ago

Try this: #6 (comment)

I tried, no changes

Zhong-Zhang commented 11 months ago

Try to alter the port of the parser server, 8080 might be occupied by other apps:

python -m sciencebeam_parser.service.server --port=7080

and the main.py:

convert_url = "http://localhost:7080/api/convert"

alexmaehon commented 11 months ago

Try to alter the port of the parser server, 8080 might be occupied by other apps:

python -m sciencebeam_parser.service.server --port=7080

and the main.py:

convert_url = "http://localhost:7080/api/convert"

changed port still not working

yuhui-zh15 commented 10 months ago

Thanks for your interest in our system. It seems this error happens when running on non-linux system. Unfortunately ScienceBeam only supports x86 Linux. Let us know if you find a way to install ScienceBeam on other systems.

yuhui-zh15 commented 10 months ago

We now added a new system that supports texts as input:

Usage:

python main_from_text.py  # If you are using non-linux operating systems or want to generate feedback from the parsed paper in text format