Skip to main content

waldiez

Project description

Waldiez

CI Build Coverage Status PyPI version

Translate a Waldiez flow:

Flow

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

Features

  • Export .waldiez flows to .py or .ipynb
  • Run a .waldiez flow
  • Include a logs folder with the logs of the flow in csv format
  • Provide a custom IOSStream to handle input and output.

Installation

On PyPI:

python -m pip install waldiez

From the repository:

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

Usage

CLI

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

# 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 --export /flow.waldiez --output /output/flow[.py|.ipynb]
# Export and run the script
$CONTAINER_COMMAND run --rm -v /path/to/a/flow.waldiez:/flow.waldiez -v /path/to/an/output:/output waldiez/waldiez /flow.waldiez --output /output/output[.py]

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)

Run a flow with a custom IOStream

# Run the flow with a custom IOStream
# In case the standard 'input' and 'print' functions cannot be used
import time
import threading

from typing import Any

from waldiez import WaldiezRunner
from waldiez.io import WaldiezIOStream

flow_path = "/path/to/a/flow.waldiez"
output_path = "/path/to/an/output.py"


def custom_print_function(*args: Any, sep: str = " ", **kwargs: Any) -> None:
    """Custom print function."""
    print(*args, sep=sep, **kwargs)


# Custom input handler
class InputProcessorWrapper:
    """Wrapper input processor.
    
    To manage the interaction between the custom input processor and IOStream.
    """

    def __init__(self):
        self.stream = None  # Placeholder for the WaldiezIOStream instance
        self.lock = threading.Lock()  # Ensure thread-safe operations

    def custom_input_processor(self, prompt: str) -> None:
        """Simulate external input and send it back to the IOStream."""
        def external_input_simulation():
            with self.lock:  # Ensure thread-safe access
                time.sleep(2)  # Simulate delay for network input
                if self.stream:
                    self.stream.set_input("Simulated external input")
                else:
                    raise RuntimeError("Stream reference not set!")

        threading.Thread(target=external_input_simulation, daemon=True).start()

    def set_stream(self, stream: "WaldiezIOStream"):
        """Set the WaldiezIOStream instance."""
        with self.lock:  # Ensure thread-safe setting of the stream
            self.stream = stream

processor_wrapper = InputProcessorWrapper()

stream = WaldiezIOStream(
    input_timeout=30,
    print_function=
    on_prompt_input=processor_wrapper.custom_input_processor,
)

# Link the processor wrapper to the WaldiezIOStream instance
processor_wrapper.set_stream(custom_stream)

with WaldiezIOStream.set_default(io_stream):
    runner = WaldiezRunner.load(flow_path)
    runner.run(stream=io_stream, output_path=output_path)

Tools

License

This project is licensed under the MIT License - see the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

waldiez-0.1.8.tar.gz (60.9 kB view details)

Uploaded Source

Built Distribution

waldiez-0.1.8-py3-none-any.whl (96.6 kB view details)

Uploaded Python 3

File details

Details for the file waldiez-0.1.8.tar.gz.

File metadata

  • Download URL: waldiez-0.1.8.tar.gz
  • Upload date:
  • Size: 60.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for waldiez-0.1.8.tar.gz
Algorithm Hash digest
SHA256 59b5b2f7e8c516297c3e40b7a986609878ed1d08a5dac1866ee9af610a896547
MD5 6ee1f4c050cfd9372d82c63d6f28cfa4
BLAKE2b-256 6218fdca57984196fb1c9103b90bbb37dce0837b12653372a40270cb59af699a

See more details on using hashes here.

Provenance

The following attestation bundles were made for waldiez-0.1.8.tar.gz:

Publisher: release.yaml on waldiez/waldiez

Attestations:

File details

Details for the file waldiez-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: waldiez-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 96.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for waldiez-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 54133f158fa29f076b5820cf3759023d1bc335aef76f00478a198dd15114c5b8
MD5 7c3402e7d9ce161ef0fa2f8846fd8f3b
BLAKE2b-256 f88c6dd0d660e81e1f3a3df1b9541b81b50948ab2dcc80c52087f5b1931800c6

See more details on using hashes here.

Provenance

The following attestation bundles were made for waldiez-0.1.8-py3-none-any.whl:

Publisher: release.yaml on waldiez/waldiez

Attestations:

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page