Skip to content

Waldiez

Waldiez

Translate a Waldiez flow:

Waldiez flow Waldiez flow

To a python script or a jupyter notebook with the corresponding ag2 agents and chats.

Features

  • Convert .waldiez flows to .py or .ipynb
  • Run a .waldiez flow
  • Store the runtime logs of a flow to csv for further analysis

Installation

On PyPI:

python -m pip install waldiez

From the repository:

python -m pip install git+https://github.com/waldiez/python.git

Note

autogen-agentchat package conflicts with ag2 / pyautogen. Ensure that autogen-agentchat is uninstalled before installing waldiez. If you have already installed autogen-agentchat, you can uninstall it with the following command:

```shell
pip uninstall autogen-agentchat -y
```

If already installed waldiez you might need to reinstall it after uninstalling `autogen-agentchat`:

```shell
pip install --force --no-cache waldiez pyautogen
```

Usage

CLI

# Convert a Waldiez flow to a python script or a jupyter notebook
waldiez convert --file /path/to/a/flow.waldiez --output /path/to/an/output/flow[.py|.ipynb]
# Convert and run the script, optionally force generation if the output file already exists
waldiez run --file /path/to/a/flow.waldiez --output /path/to/an/output/flow[.py] [--force]

Using docker/podman

CONTAINER_COMMAND=docker # or podman
# pull the image
$CONTAINER_COMMAND pull waldiez/waldiez
# Convert a Waldiez flow to a python script or a jupyter notebook
$CONTAINER_COMMAND run \
  --rm \
  -v /path/to/a/flow.waldiez:/flow.waldiez \
  -v /path/to/an/output:/output \
  waldiez/waldiez convert --file /flow.waldiez --output /output/flow[.py|.ipynb] [--force]

# with selinux and/or podman, you might get permission (or file not found) errors, so you can try:
$CONTAINER_COMMAND run \
  --rm \
  -v /path/to/a/flow.waldiez:/flow.waldiez \
  -v /path/to/an/output:/output \
  --userns=keep-id \
  --security-opt label=disable \
  waldiez/waldiez convert --file /flow.waldiez --output /output/flow[.py|.ipynb] [--force]

# Convert and run the script
$CONTAINER_COMMAND run \
  --rm \
  -v /path/to/a/flow.waldiez:/flow.waldiez \
  -v /path/to/an/output:/output \
  waldiez/waldiez run --file /flow.waldiez --output /output/output[.py]

UI

For creating-only (no exporting or running) waldiez flows, you can use the playground at https://waldiez.github.io. The repo for the js library is here. We are currently working on waldiez-studio to provide a visual interface for creating and running Waldiez flows (you can find more here). Until then, you can use our Jupyter or the VSCode extension to create and run Waldiez flows.

As a library

Export a flow
# Export a Waldiez flow to a python script or a jupyter notebook
from waldiez import WaldiezExporter
flow_path = "/path/to/a/flow.waldiez"
output_path = "/path/to/an/output.py"  # or .ipynb
exporter = WaldiezExporter.load(flow_path)
exporter.export(output_path)
Run a flow
# Run a flow
from waldiez import WaldiezRunner
flow_path = "/path/to/a/flow.waldiez"
output_path = "/path/to/an/output.py"
runner = WaldiezRunner.load(flow_path)
runner.run(output_path=output_path)

Tools