About Plato RDS

Plato Research Dialogue System is a platform for building, training, and deploying conversational AI agents that allows us to conduct state of the art research in conversational AI, quickly create prototypes and demonstration systems, as well as facilitate conversational data collection. Read more

How does it work?

Install

Clone the following repository: git@github.com:uber-research/
plato-research-dialogue-system.git

For MacOS:
brew install portaudio
pip install -r requirements.txt

For Ubuntu/Debian:
sudo apt-get install python3-pyaudio
pip install -r requirements.txt

For Windows:
pip install -r requirements.txt

Running Single Agents

To run a simulation:
python runPlatoRDS.py
-config Examples/config/simulate_agenda.yaml

To run a text based interaction:
python runPlatoRDS.py
-config Examples/config/simulate_text.yaml

To run a speech based interaction:
python runPlatoRDS.py
-config Examples/config/simulate_speech.yaml

Training Multiple Agents

python runPlatoRDS.py
-config Examples/config/CamRest_MA_train.yaml

python runPlatoRDS.py
-config Examples/config/CamRest_MA_test.yaml

Training with Ludwig

Ludwig is a toolbox that allows to train and test
deep learning models without the need to write code. Briefly, you need to do the following:

1. Prepare your data in csv format.
2. Train your model with Ludwig
3. Update your Plato configuration file to include the path to the ludwig model
4. Run a Plato agent. For a walk-through, look at the User Guide