Smart eDiscovery using Large Language Model with Streamlit
This project implemented using Langchain framework and Chroma DB, an open-source embedding database. It uses LaMini-T5-738M model a fine-tuned version of t5-large on LaMini-instruction dataset which contains 2.58M samples for instruction fine-tuning.
To install the requirements for this project, run the following command:
$ pip install -r requirements.txtTo use this project, run the app.py script
$ streamlit run app.py