AILA is a prototypical webapp for information retrieval (IR) and question answering (QA) in German legal documents.
Legal systems form the foundation of democratic states. Nevertheless, it is nearly impossible for individuals to extract specific information from comprehensive legal documents. AILA takes first steps towards an AI-supported system for IR and QA in the German legal domain. Laypersons and legal professionals receive information supporting their research and decision-making by interacting with the architecture using a graphical interface. The internal language models are trained on our own annotated LegalSQuAD dataset, evaluating complex context-based search terms, considering German law-specific words and phrases.
You can download a copy of all the files in this repository by cloning the git repository:
git clone https://github.com/Christoph911/ailegaladvisor.git
- Clone Repository
- Create your virtual environment
- Install requirements
- Setup a document database (e.g. ElasticSearch)
- Have fun :)
- Python (https://www.python.org)
- Deepst-Haystack (https://www.deepset.ai/haystack)
- ElasticSearch (https://www.elastic.co/de/elasticsearch/)
- Streamlit (https://streamlit.io)
- Huggingface (https://huggingface.co)
All source code is made available under a MIT-license. You can freely use and modify the code, without warranty, so long as you provide attribution to the authors.
If you have any questions, ideas or just want to say hi, please feel free to contact us.