unstructured

ISW Summarization Example

This directory shows and example of how to use unstructured, argilla, and transformers to train a custom summarization model on Institute for the Study of War (ISW) reports about the was in Ukraine. This example shows how, by combining these three libraries, you can complete a data science project in hours that previously would have taken weeks.

To get started, use the following steps:

• Ensure you have Python 3.10 or higher installed on your system
• Create a new Python virtual environment
• Run pip install -r requirements.txt to install the dependencies
• Run PYTHONPATH=. jupyter notebook from this directory to launch the notebook

At this point, you'll be able to run the model training notebook.