An AG2 (formerly Autogen) extension that allows code execution using YepCode's secure serverless runtime
Project description
AG2 Extension for YepCode
An AG2 (formerly AutoGen) extension that enables secure code execution using YepCode's serverless runtime environment. Execute Python and JavaScript code in production-grade, isolated sandboxes with built-in security and scalability.
Note: AG2 was evolved from AutoGen. If you are looking for the extension for AutoGen, please check the autogen-ext-yepcode repository.
Features
- Secure Execution: Code runs in isolated, production-grade sandboxes
- Multi-language Support: Python and JavaScript execution
- Automatic Package Installation: YepCode automatically detects and installs dependencies in the sandbox
- Logging and Monitoring: Access to YepCode's execution logs, results and errors
- AG2 Integration: Seamless integration with AG2 agents and tools
Installation
Install the package using pip:
pip install ag2_ext_yepcode
Setup
- Create a YepCode Account: Sign up at yepcode.io
- Get Your API Token: Navigate to
Settings>API credentialsin your YepCode workspace - Set Environment Variable:
export YEPCODE_API_TOKEN="your-api-token-here"
Alternatively, you can pass the API token directly to the executor constructor.
Quick Start
Basic Integration with AG2
The YepCode executor is designed to work with AG2 agents as a CodeExecutor. Here's a example of just the code executor agent:
from autogen import ConversableAgent, LLMConfig
from ag2_ext_yepcode import YepCodeCodeExecutor
from dotenv import load_dotenv
import os
# Load environment variables from .env file if it exists
load_dotenv()
# Initialize YepCode executor
yepcode_executor = YepCodeCodeExecutor(
timeout=120,
remove_on_done=False,
sync_execution=True,
)
# Create an agent with code executor configuration.
code_executor_agent = ConversableAgent(
"code_executor_agent",
llm_config=False, # Turn off LLM for this agent.
code_execution_config={
"executor": yepcode_executor
}, # Use the local command line code executor.
human_input_mode="ALWAYS", # Always take human input for this agent for safety.
)
task = """Run this code:
\```python
message = "Hello, world!"
print(message)
return message
\```
and return the output.
"""
# Generate a reply for the given code.
reply = code_executor_agent.generate_reply(messages=[{"role": "user", "content": task}])
print(reply)
With LLMs and code execution tools
The extension also works with more advanced patterns, like using LLMs and code execution tools:
from autogen import ConversableAgent, LLMConfig
from ag2_ext_yepcode import YepCodeCodeExecutor
from dotenv import load_dotenv
import os
# Load environment variables from .env file if it exists
load_dotenv()
# Initialize YepCode executor
yepcode_executor = YepCodeCodeExecutor(
timeout=120,
remove_on_done=False,
sync_execution=True,
)
# Create an agent with code executor configuration.
code_executor_agent = ConversableAgent(
"code_executor_agent",
llm_config=False, # Turn off LLM for this agent.
code_execution_config={
"executor": yepcode_executor
}, # Use the local command line code executor.
human_input_mode="ALWAYS",
)
# The code writer agent's system message is to instruct the LLM on how to use
# the code executor in the code executor agent.
code_writer_system_message = """You are a helpful AI assistant.
Solve tasks using your coding and language skills.
In the following cases, suggest python code (in a python coding block) for the user to execute.
1. When you need to collect info, use the code to output the info you need. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.
2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.
Solve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.
When using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can't modify your code. So do not suggest incomplete code which requires users to modify. Don't use a code block if it's not intended to be executed by the user.
If the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can't be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.
When you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.
Reply 'TERMINATE' in the end when everything is done.
"""
code_writer_agent = ConversableAgent(
"code_writer_agent",
system_message=code_writer_system_message,
llm_config=LLMConfig(
api_type="anthropic",
model="claude-3-haiku-20240307",
api_key=os.environ["ANTHROPIC_API_KEY"],
),
code_execution_config=False, # Turn off code execution for this agent.
)
chat_result = code_executor_agent.initiate_chat(
code_writer_agent,
message="Fetch cryptocurrency price data from a public API and analyze the top 5 cryptocurrencies by market cap. Use the requests library to get data and calculate some basic statistics.",
)
print(chat_result)
Custom Configuration
You can customize the YepCode executor behavior:
# Custom executor configuration
yepcode_executor = YepCodeCodeExecutor(
api_token="your-api-token", # Optional: pass token directly
timeout=300, # 5 minutes timeout
remove_on_done=False, # Keep execution records for debugging
sync_execution=True, # Wait for completion
)
API Reference
YepCodeCodeExecutor
The main executor class for running code in YepCode's serverless environment.
Constructor Parameters
api_token(Optional[str]): YepCode API token. If not provided, will useYEPCODE_API_TOKENenvironment variable.timeout(int): Execution timeout in seconds. Default: 60.remove_on_done(bool): Whether to remove execution records after completion. Default: True.sync_execution(bool): Whether to wait for execution completion. Default: True.
Methods
async execute_code_blocks(code_blocks, cancellation_token): Execute code blocks
YepCodeCodeResult
Result object returned from code execution.
Properties
exit_code(int): Execution exit code (0 for success)output(str): Execution output and logsexecution_id(Optional[str]): YepCode execution ID for tracking
Supported Languages
| Language | Language Code | Aliases |
|---|---|---|
| Python | python |
py |
| JavaScript | javascript |
js |
Development
Setup Development Environment
git clone https://github.com/yepcode/ag2_ext_yepcode.git
cd ag2_ext_yepcode
poetry install
Run Tests
pytest tests/ -v
📚 Documentation
- YepCode Documentation: Complete YepCode platform documentation
- AG2 Documentation: AG2 framework documentation
License
This project is licensed under the MIT License - see the LICENSE file for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ag2_ext_yepcode-0.1.0.tar.gz.
File metadata
- Download URL: ag2_ext_yepcode-0.1.0.tar.gz
- Upload date:
- Size: 6.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.3 CPython/3.12.11 Linux/6.11.0-1015-azure
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
15ea131c22176da818d866caa6bf8db5eee9e36972a10031e2b03cf693d5d402
|
|
| MD5 |
37d89687d60c4e635af1223e77fbcce5
|
|
| BLAKE2b-256 |
97b898a505a376a2337f640096815e2194ca7471d39df43fae91b9b1c950ed5f
|
File details
Details for the file ag2_ext_yepcode-0.1.0-py3-none-any.whl.
File metadata
- Download URL: ag2_ext_yepcode-0.1.0-py3-none-any.whl
- Upload date:
- Size: 7.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.3 CPython/3.12.11 Linux/6.11.0-1015-azure
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9cb73dbf93ebe9958bb7ecb58904d05a538dff6e24bb1da02f74dd3a033576b3
|
|
| MD5 |
7987edf0c20d087b11d01fb25c8a91f7
|
|
| BLAKE2b-256 |
ed44d58f215b12262acf308c5b022446e5728f37ef3efe60f12ff9918e82861f
|