Skip to content

VIDA-NYU/data-gatherer

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

56 Commits
html_xml_samples/PMC
html_xml_samples/PMC
 
 
input
input
 
 
logs
logs
 
 
output
output
 
 
prompts
prompts
 
 
staging_table
staging_table
 
 
Data_Gatherer_Demo.ipynb
Data_Gatherer_Demo.ipynb
 
 
LLMs_responses.json
LLMs_responses.json
 
 
README.md
README.md
 
 
classifier.py
classifier.py
 
 
classifier_patterns.json
classifier_patterns.json
 
 
config.json
config.json
 
 
config_xml.json
config_xml.json
 
 
data_fetcher.py
data_fetcher.py
 
 
logger_setup.py
logger_setup.py
 
 
main.py
main.py
 
 
orchestrator.py
orchestrator.py
 
 
parser.py
parser.py
 
 
performance_evaluation.ipynb
performance_evaluation.ipynb
 
 
prompt_manager.py
prompt_manager.py
 
 
requirements.txt
requirements.txt
 
 
selenium_setup.py
selenium_setup.py
 
 
try.py
try.py
 
 

Repository files navigation

data-gatherer

The Data Gatherer Tool is designed for automating the extraction of datasets from scientific articles webpages. It integrates LLMs, dynamic prompt management, and rule-based parsing, to facilitate data harmonization in biomedical research, and hopefully other domains.

About

No description, website, or topics provided.

Resources

Readme
Activity
Custom properties

Stars

0 stars

Watchers

6 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages