Skip to content

max-planck-innovation-competition/logic-mill

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LM Logo

Logic Mill - A Knowledge Navigation System

Logic Mill is a scalable and openly accessible software system that identifies semantically similar documents within either one domain-specific corpus or multi-domain corpora. It uses advanced Natural Language Processing (NLP) techniques to generate numerical representations of documents. Currently, it leverages a large pre-trained language model to generate these document representations. The system focuses on scientific publications and patent documents and contains more than 200 million documents. It is easily accessible via a simple Application Programming Interface (API) or via a web interface. Moreover, it is continuously being updated and can be extended to text corpora from other domains. We see this system as a general-purpose tool for future research applications in the social sciences and other domains.

This repository contains public documentation and code examples for the use of the API. This is also the place to post issues and feature requests.

Waiting list

Logic Mill is still in beta.

You can sign up for the Logic Mill waiting list. Signing up for the waiting list does not automatically give you access to the system.

API key

In order to use the Logic Mill endpoint you need an API key. Check your profile (top right) once you are logged in and copy the key into your code.

Examples

In the /src directory you will find examples no how to use the Logic Mill API in several languages. We have examples in:

  • Go
  • Python
    • basic-api-usage.ipynb: basic Python examples
    • automatic_parsing.py: automatically flattens the nested response to a data frame. This code has not been thoroughly tested yet.
  • R
  • Stata (using Python)
    • LogicMill.do: .do file where the python is integrated
    • external.do: .do file with external python files (external.py and logic_mill.py). It also has automated flattening of the JSON response. Not completely tested.
    • When running/integrating with Stata you probably also want to take a look at the Python examples for the different endpoints and the code for flattening the data.
  • Javascript. No specific examples have been added, but the Logic Mill website has Javascript as one of the previews.

Bug reports and feature requests

If you found an error in our API or have a request to improve our system, please let us know! You can add those as an issue in this GitHub repository:

Create a request

URLs

Paper

If you use the Logic Mill system, please cite our paper: https://doi.org/10.48550/arXiv.2301.00200:

@misc{erhardt2022logic,
      title={Logic Mill - A Knowledge Navigation System},
      author={Sebastian Erhardt and Mainak Ghosh and Erik Buunk and Michael E. Rose and Dietmar Harhoff},
      year={2022},
      eprint={2301.00200},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

https://arxiv.org/abs/2301.00200

Contact

© 2023 Max Planck Institute for Innovation and Competition. All rights reserved.

About

Public Repository for Logic Mill

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published