1578cd955f
Currently when an error occurs when executing code in docker jupyter executor, it returns only the error output. This PR updates the handling of error output to include outputs from previous code blocks that have been successfully executed. Test it with this script: ```python from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.code_executors.docker_jupyter import DockerJupyterCodeExecutor, DockerJupyterServer from autogen_ext.tools.code_execution import PythonCodeExecutionTool from autogen_agentchat.ui import Console from autogen_core.code_executor import CodeBlock from autogen_core import CancellationToken from autogen_agentchat.teams import RoundRobinGroupChat from autogen_agentchat.conditions import TextMessageTermination # Download the dataset from https://www.kaggle.com/datasets/nelgiriyewithana/top-spotify-songs-2023 # and place it the coding directory as `spotify-2023.csv`. bind_dir = "./coding" # Use a custom docker image with the Jupyter kernel gateway and data science libraries installed. # Custom docker image: ds-kernel-gateway:latest -- you need to build this image yourself. # Dockerfile: # FROM quay.io/jupyter/docker-stacks-foundation:latest # # # ensure that 'mamba' and 'fix-permissions' are on the PATH # SHELL ["/bin/bash", "-o", "pipefail", "-c"] # # # Switch to the default notebook user # USER ${NB_UID} # # # Install data-science packages + kernel gateway # RUN mamba install --quiet --yes \ # numpy \ # pandas \ # scipy \ # matplotlib \ # scikit-learn \ # seaborn \ # jupyter_kernel_gateway \ # ipykernel \ # && mamba clean --all -f -y \ # && fix-permissions "${CONDA_DIR}" \ # && fix-permissions "/home/${NB_USER}" # # # Allow you to set a token at runtime (or leave blank for no auth) # ENV TOKEN="" # # # Launch the Kernel Gateway, listening on all interfaces, # # with the HTTP endpoint for listing kernels enabled # CMD ["python", "-m", "jupyter", "kernelgateway", \ # "--KernelGatewayApp.ip=0.0.0.0", \ # "--KernelGatewayApp.port=8888", \ # # "--KernelGatewayApp.auth_token=${TOKEN}", \ # "--JupyterApp.answer_yes=true", \ # "--JupyterWebsocketPersonality.list_kernels=true"] # # EXPOSE 8888 # # WORKDIR "${HOME}" async def main(): model = OpenAIChatCompletionClient(model="gpt-4.1") async with DockerJupyterServer( custom_image_name="ds-kernel-gateway:latest", bind_dir=bind_dir, ) as server: async with DockerJupyterCodeExecutor(jupyter_server=server) as code_executor: await code_executor.execute_code_blocks([ CodeBlock(code="import pandas as pd\ndf = pd.read_csv('/workspace/spotify-2023.csv', encoding='latin-1')", language="python"), ], cancellation_token=CancellationToken(), ) tool = PythonCodeExecutionTool( executor=code_executor, ) assistant = AssistantAgent( "assistant", model_client=model, system_message="You have access to a Jupyter kernel. Do not write all code at once. Write one code block, observe the output, and then write the next code block.", tools=[tool], ) team = RoundRobinGroupChat( [assistant], termination_condition=TextMessageTermination(source="assistant"), ) task = f"Datafile has been loaded as variable `df`. First preview dataset. Then answer the following question: What is the highest streamed artist in the dataset?" await Console(team.run_stream(task=task)) if __name__ == "__main__": import asyncio asyncio.run(main()) ``` You can see the file encoding error gets recovered and the agent successfully executes the query in the end.
AutoGen Python packages
This directory works as a single uv workspace containing all project packages. See packages to discover all project packages.
Migrating from 0.2.x?
Please refer to the migration guide for how to migrate your code from 0.2.x to 0.4.x.
Development
TL;DR, run all checks with:
uv sync --all-extras
source .venv/bin/activate
poe check
Setup
uv is a package manager that assists in creating the necessary environment and installing packages to run AutoGen.
Note: To prevent incompatibilities between versions the same UV version as is running in CI should be used. Check the version in CI by looking the setup-uv action, here for example.
For example, to change your version to 0.5.18, run:
uv self update 0.5.18
Virtual Environment
During development, you may need to test changes made to any of the packages.
To do so, create a virtual environment where the AutoGen packages are installed based on the current state of the directory.
Run the following commands at the root level of the Python directory:
uv sync --all-extras
source .venv/bin/activate
uv sync --all-extraswill create a.venvdirectory at the current level and install packages from the current directory along with any other dependencies. Theall-extrasflag adds optional dependencies.source .venv/bin/activateactivates the virtual environment.
Common Tasks
To create a pull request (PR), ensure the following checks are met. You can run each check individually:
- Format:
poe format - Lint:
poe lint - Test:
poe test - Mypy:
poe mypy - Pyright:
poe pyright - Build docs:
poe --directory ./packages/autogen-core/ docs-build - Auto rebuild+serve docs:
poe --directory ./packages/autogen-core/ docs-serve - Check samples in
python/samples:poe samples-code-checkAlternatively, you can run all the checks with: poe check
Note
These need to be run in the virtual environment.
Syncing Dependencies
When you pull new changes, you may need to update the dependencies.
To do so, first make sure you are in the virtual environment, and then in the python directory, run:
uv sync --all-extras
This will update the dependencies in the virtual environment.
Creating a New Package
To create a new package, similar to autogen-core or autogen-chat, use the following:
uv sync --python 3.12
source .venv/bin/activate
cookiecutter ./templates/new-package/