talktrace 0.3

Evaluating in-classroom teaching simulations leveraging the power of large language models.

About TalkTrace

TalkTrace is an open-source, platform independent webapp for evaluating the performance of teaching students during class room simulation, leveraging the power of Large Language Models (LLMs). It will provide both quantitative and qualitative reports of the verbal classroom performance and allows for customization of the analysis parameters. It was built Shiny for Python web application. It provides an interactive web interface for users to engage with data and visualizations. An API-Key for either OpenAI or groq is required to perform qualitative analysis.

Installation

Install the TalkTrace package on your python 3 via

pip install talktrace

In some scenarios, you may need to run

python3 -m pip install talktrace

Usage

To run the web application, from terminal simply run

talktrace

or

python3 -m talktrace

Once the application is running, it will automatically open the interface in your webbrowser at http://localhost:8000.

Contributing

Contributions are welcome! Please submit a pull request or open an issue for any enhancements or bug fixes on github.

License

This project is licensed under the CC BY-NC 4.0 License. See the LICENSE file for more details. Let's socialize software for the open-source democratic stack!