You've already forked adk-python
mirror of
https://github.com/encounter/adk-python.git
synced 2026-03-30 10:57:20 -07:00
Artem Oroberts
edfe553942
This change introduces a new sample agent and documentation to demonstrate the usage of the `VertexAiCodeExecutor`. The new agent, located at `vertex_code_execution/agent.py`, is a direct counterpart to the existing sample at `code_execution/agent.py`. The key difference is that this new agent uses `VertexAiCodeExecutor` to execute code within the Vertex AI Code Interpreter Extension, whereas the original sample uses `BuiltInCodeExecutor` to run code in the model's built-in sandbox. A `README.md` file is also included to provide an overview, setup instructions, and sample usage for the new agent. Related: #2993 PiperOrigin-RevId: 825239758
60 lines
2.1 KiB
Markdown
60 lines
2.1 KiB
Markdown
# Vertex AI Code Execution Agent Sample
|
|
|
|
This directory contains a sample agent that demonstrates how to use the
|
|
`VertexAiCodeExecutor` for data science tasks.
|
|
|
|
## Overview
|
|
|
|
The agent is designed to assist with data analysis in a Python environment. It
|
|
can execute Python code to perform tasks like data manipulation, analysis, and
|
|
visualization. This agent is particularly useful for tasks that require a secure
|
|
and sandboxed code execution environment with common data science libraries
|
|
pre-installed.
|
|
|
|
This sample is a direct counterpart to the
|
|
[code execution sample](../code_execution/) which uses the
|
|
`BuiltInCodeExecutor`. The key difference in this sample is the use of
|
|
`VertexAiCodeExecutor`.
|
|
|
|
## `VertexAiCodeExecutor`
|
|
|
|
The `VertexAiCodeExecutor` leverages the
|
|
[Vertex AI Code Interpreter Extension](https://cloud.google.com/vertex-ai/generative-ai/docs/extensions/code-interpreter)
|
|
to run Python code. This provides several advantages:
|
|
|
|
- **Security**: Code is executed in a sandboxed environment on Google Cloud,
|
|
isolating it from your local system.
|
|
- **Pre-installed Libraries**: The environment comes with many common Python
|
|
data science libraries pre-installed, such as `pandas`, `numpy`, and
|
|
`matplotlib`.
|
|
- **Stateful Execution**: The execution environment is stateful, meaning
|
|
variables and data from one code execution are available in subsequent
|
|
executions within the same session.
|
|
|
|
## How to use
|
|
|
|
### Prerequisites
|
|
|
|
Ensure you have configured your environment for using
|
|
[Google Cloud Vertex AI](https://google.github.io/adk-docs/get-started/quickstart/#gemini---google-cloud-vertex-ai).
|
|
You will need to have a Google Cloud Project with the Vertex AI API enabled.
|
|
|
|
### Running the agent
|
|
|
|
You can run this agent using the ADK CLI from the root of the repository.
|
|
|
|
To interact with the agent through the command line:
|
|
|
|
```bash
|
|
adk run contributing/samples/vertex_code_execution "Plot a sine wave from 0 to 10"
|
|
```
|
|
|
|
To use the web interface:
|
|
|
|
```bash
|
|
adk web contributing/samples/
|
|
```
|
|
|
|
Then select `vertex_code_execution` from the list of agents and interact with
|
|
it.
|