| Name | sysbox JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | https://github.com/vndee/sysbox |
| Summary | Lightweight and portable sandbox runtime (code interpreter) Python library |
| upload_time | 2024-09-01 20:33:05 |
| maintainer | None |
| docs_url | None |
| author | Mark Powers |
| requires_python | >=3.7 |
| license | None |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Sysbox v0.1.2
*Securely Execute LLM-Generated Code with Ease*
Sysbox is a lightweight and portable sandbox environment designed to run large language model (LLM) generated code in a safe and isolated manner using Docker containers or Kubernetes. This project provides an easy-to-use interface for setting up, managing, and executing code in a controlled environment, simplifying the process of running code generated by LLMs.
### Features
- **Easy Setup:** Quickly create sandbox environments with minimal configuration.
- **Isolation:** Run your code in isolated Docker containers to prevent interference with your host system.
- **Flexibility:** Support for multiple programming languages.
- **Portability:** Use predefined Docker images or custom Dockerfiles.
- **Scalability:** Support Kubernetes and remote Docker host.
### Installation
#### Using pip
1. Ensure you have [pip](https://pip.pypa.io/en/stable/installation/) installed.
2. Install the package:
```sh
pip install sysbox
```
### Usage
#### Session Lifecycle
The `SandboxSession` class manages the lifecycle of the sandbox environment, including the creation and destruction of Docker containers. Here’s a typical lifecycle:
1. **Initialization:** Create a `SandboxSession` object with the desired configuration.
2. **Open Session:** Call the `open()` method to build/pull the Docker image and start the Docker container.
3. **Run Code:** Use the `run()` method to execute code inside the sandbox. Currently, it supports Python, Java, JavaScript, C++, Go, and Ruby. See [examples](examples) for more details.
4. **Close Session:** Call the `close()` method to stop and remove the Docker container. If the `keep_template` flag is set to `True`, the Docker image will not be removed, and the last container state will be committed to the image.
### Example
Here's a simple example to demonstrate how to use sysbox:
```python
from sysbox import SandboxSession
# Create a new sandbox session
with SandboxSession(image="python:3.9.19-bullseye", keep_template=True, lang="python") as session:
result = session.run("print('Hello, World!')")
print(result)
# With custom Dockerfile
with SandboxSession(dockerfile="Dockerfile", keep_template=True, lang="python") as session:
result = session.run("print('Hello, World!')")
print(result)
# Or default image
with SandboxSession(lang="python", keep_template=True) as session:
result = session.run("print('Hello, World!')")
print(result)
```
sysbox also supports copying files between the host and the sandbox:
```python
from sysbox import SandboxSession
with SandboxSession(lang="python", keep_template=True) as session:
# Copy a file from the host to the sandbox
session.copy_to_runtime("test.py", "/sandbox/test.py")
# Run the copied Python code in the sandbox
result = session.run("python /sandbox/test.py")
print(result)
# Copy a file from the sandbox to the host
session.copy_from_runtime("/sandbox/output.txt", "output.txt")
```
For other languages usage, please refer to the [examples](examples/code_runner_docker.py).
You can also use [remote Docker host](https://docs.docker.com/config/daemon/remote-access/) as below:
```python
import docker
from sysbox import SandboxSession
tls_config = docker.tls.TLSConfig(
client_cert=("path/to/cert.pem", "path/to/key.pem"),
ca_cert="path/to/ca.pem",
verify=True
)
docker_client = docker.DockerClient(base_url="tcp://<your_host>:<port>", tls=tls_config)
with SandboxSession(
client=docker_client,
image="python:3.9.19-bullseye",
keep_template=True,
lang="python",
) as session:
result = session.run("print('Hello, World!')")
print(result)
```
For Kubernetes usage, please refer to the examples. Essentially, you just need to set the use_kubernetes flag to True and provide the Kubernetes client, or leave it as the default for the local context.
#### Integration
With Langchain integration, you can easily run the generated code in a safe and isolated environment. Here's an example of how to use sysbox with Langchain:
```python
from typing import Optional, List
from sysbox import SandboxSession
from langchain import hub
from langchain_openai import ChatOpenAI
from langchain.tools import tool
from langchain.agents import AgentExecutor, create_tool_calling_agent
@tool
def run_code(lang: str, code: str, libraries: Optional[List] = None) -> str:
"""
Run code in a sandboxed environment.
:param lang: The language of the code.
:param code: The code to run.
:param libraries: The libraries to use, it is optional.
:return: The output of the code.
"""
with SandboxSession(lang=lang, verbose=False) as session: # type: ignore[attr-defined]
return session.run(code, libraries).text
if __name__ == "__main__":
llm = ChatOpenAI(model="gpt-4o", temperature=0)
prompt = hub.pull("hwchase17/openai-functions-agent")
tools = [run_code]
agent = create_tool_calling_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
output = agent_executor.invoke(
{
"input": "Write python code to calculate Pi number by Monte Carlo method then run it."
}
)
print(output)
output = agent_executor.invoke(
{
"input": "Write python code to calculate the factorial of a number then run it."
}
)
print(output)
output = agent_executor.invoke(
{"input": "Write python code to calculate the Fibonacci sequence then run it."}
)
print(output)
```
For Llama-Index:
```python
from typing import Optional, List
from sysbox import SandboxSession
from llama_index.llms.openai import OpenAI
from llama_index.core.tools import FunctionTool
from llama_index.core.agent import FunctionCallingAgentWorker
import nest_asyncio
nest_asyncio.apply()
def run_code(lang: str, code: str, libraries: Optional[List] = None) -> str:
"""
Run code in a sandboxed environment.
:param lang: The language of the code, must be one of ['python', 'java', 'javascript', 'cpp', 'go', 'ruby'].
:param code: The code to run.
:param libraries: The libraries to use, it is optional.
:return: The output of the code.
"""
with SandboxSession(lang=lang, verbose=False) as session: # type: ignore[attr-defined]
return session.run(code, libraries).text
if __name__ == "__main__":
llm = OpenAI(model="gpt-4o", temperature=0)
code_execution_tool = FunctionTool.from_defaults(fn=run_code)
agent_worker = FunctionCallingAgentWorker.from_tools(
[code_execution_tool],
llm=llm,
verbose=True,
allow_parallel_tool_calls=False,
)
agent = agent_worker.as_agent()
response = agent.chat(
"Write python code to calculate Pi number by Monte Carlo method then run it."
)
print(response)
response = agent.chat(
"Write python code to calculate the factorial of a number then run it."
)
print(response)
response = agent.chat(
"Write python code to calculate the Fibonacci sequence then run it."
)
print(response)
response = agent.chat("Calculate the sum of the first 10000 numbers.")
print(response)
```
### Contributing
We welcome contributions to improve sysbox! Since I am a Python developer, I am not familiar with other languages. If you are interested in adding better support for other languages, please feel free to submit a pull request.
Here is a list of things you can do to contribute:
- [ ] Add Java maven support.
- [x] Add support for JavaScript.
- [x] Add support for C++.
- [x] Add support for Go.
- [ ] Add support for Ruby.
- [x] Add remote Docker host support.
- [x] Add remote Kubernetes cluster support.
- [x] Langchain integration.
- [x] LlamaIndex integration.
- [ ] Commit the last container state to the image before closing kubernetes session.
### License
This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": "https://github.com/vndee/sysbox",
"name": "sysbox",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": null,
"author": "Mark Powers",
"author_email": "mpoweru@lifsys.com",
"download_url": "https://files.pythonhosted.org/packages/18/2c/5a3ca97c69af829e791d04b3690710802a7ed236bdb9944584eb2e731137/sysbox-0.1.2.tar.gz",
"platform": null,
"description": "# Sysbox v0.1.2\n\n*Securely Execute LLM-Generated Code with Ease*\n\nSysbox is a lightweight and portable sandbox environment designed to run large language model (LLM) generated code in a safe and isolated manner using Docker containers or Kubernetes. This project provides an easy-to-use interface for setting up, managing, and executing code in a controlled environment, simplifying the process of running code generated by LLMs.\n\n\n### Features\n\n- **Easy Setup:** Quickly create sandbox environments with minimal configuration.\n- **Isolation:** Run your code in isolated Docker containers to prevent interference with your host system.\n- **Flexibility:** Support for multiple programming languages.\n- **Portability:** Use predefined Docker images or custom Dockerfiles.\n- **Scalability:** Support Kubernetes and remote Docker host.\n\n### Installation\n\n#### Using pip\n\n1. Ensure you have [pip](https://pip.pypa.io/en/stable/installation/) installed.\n2. Install the package:\n\n```sh\npip install sysbox\n```\n\n### Usage\n\n#### Session Lifecycle\n\nThe `SandboxSession` class manages the lifecycle of the sandbox environment, including the creation and destruction of Docker containers. Here\u2019s a typical lifecycle:\n\n1. **Initialization:** Create a `SandboxSession` object with the desired configuration.\n2. **Open Session:** Call the `open()` method to build/pull the Docker image and start the Docker container.\n3. **Run Code:** Use the `run()` method to execute code inside the sandbox. Currently, it supports Python, Java, JavaScript, C++, Go, and Ruby. See [examples](examples) for more details.\n4. **Close Session:** Call the `close()` method to stop and remove the Docker container. If the `keep_template` flag is set to `True`, the Docker image will not be removed, and the last container state will be committed to the image.\n\n### Example\n\nHere's a simple example to demonstrate how to use sysbox:\n\n```python\nfrom sysbox import SandboxSession\n\n# Create a new sandbox session\nwith SandboxSession(image=\"python:3.9.19-bullseye\", keep_template=True, lang=\"python\") as session:\n result = session.run(\"print('Hello, World!')\")\n print(result)\n\n# With custom Dockerfile\nwith SandboxSession(dockerfile=\"Dockerfile\", keep_template=True, lang=\"python\") as session:\n result = session.run(\"print('Hello, World!')\")\n print(result)\n\n# Or default image\nwith SandboxSession(lang=\"python\", keep_template=True) as session:\n result = session.run(\"print('Hello, World!')\")\n print(result)\n```\n\n\nsysbox also supports copying files between the host and the sandbox:\n\n```python\nfrom sysbox import SandboxSession\n\nwith SandboxSession(lang=\"python\", keep_template=True) as session:\n # Copy a file from the host to the sandbox\n session.copy_to_runtime(\"test.py\", \"/sandbox/test.py\")\n\n # Run the copied Python code in the sandbox\n result = session.run(\"python /sandbox/test.py\")\n print(result)\n\n # Copy a file from the sandbox to the host\n session.copy_from_runtime(\"/sandbox/output.txt\", \"output.txt\")\n```\n\nFor other languages usage, please refer to the [examples](examples/code_runner_docker.py).\n\nYou can also use [remote Docker host](https://docs.docker.com/config/daemon/remote-access/) as below:\n\n```python\nimport docker\nfrom sysbox import SandboxSession\n\ntls_config = docker.tls.TLSConfig(\n client_cert=(\"path/to/cert.pem\", \"path/to/key.pem\"),\n ca_cert=\"path/to/ca.pem\",\n verify=True\n)\ndocker_client = docker.DockerClient(base_url=\"tcp://<your_host>:<port>\", tls=tls_config)\n\nwith SandboxSession(\n client=docker_client,\n image=\"python:3.9.19-bullseye\",\n keep_template=True,\n lang=\"python\",\n) as session:\n result = session.run(\"print('Hello, World!')\")\n print(result)\n```\n\nFor Kubernetes usage, please refer to the examples. Essentially, you just need to set the use_kubernetes flag to True and provide the Kubernetes client, or leave it as the default for the local context.\n\n#### Integration\nWith Langchain integration, you can easily run the generated code in a safe and isolated environment. Here's an example of how to use sysbox with Langchain:\n\n```python\nfrom typing import Optional, List\nfrom sysbox import SandboxSession\nfrom langchain import hub\nfrom langchain_openai import ChatOpenAI\nfrom langchain.tools import tool\nfrom langchain.agents import AgentExecutor, create_tool_calling_agent\n\n\n@tool\ndef run_code(lang: str, code: str, libraries: Optional[List] = None) -> str:\n \"\"\"\n Run code in a sandboxed environment.\n :param lang: The language of the code.\n :param code: The code to run.\n :param libraries: The libraries to use, it is optional.\n :return: The output of the code.\n \"\"\"\n with SandboxSession(lang=lang, verbose=False) as session: # type: ignore[attr-defined]\n return session.run(code, libraries).text\n\n\nif __name__ == \"__main__\":\n llm = ChatOpenAI(model=\"gpt-4o\", temperature=0)\n prompt = hub.pull(\"hwchase17/openai-functions-agent\")\n tools = [run_code]\n\n agent = create_tool_calling_agent(llm, tools, prompt)\n agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n output = agent_executor.invoke(\n {\n \"input\": \"Write python code to calculate Pi number by Monte Carlo method then run it.\"\n }\n )\n print(output)\n\n output = agent_executor.invoke(\n {\n \"input\": \"Write python code to calculate the factorial of a number then run it.\"\n }\n )\n print(output)\n\n output = agent_executor.invoke(\n {\"input\": \"Write python code to calculate the Fibonacci sequence then run it.\"}\n )\n print(output)\n```\n\nFor Llama-Index:\n```python\nfrom typing import Optional, List\nfrom sysbox import SandboxSession\n\nfrom llama_index.llms.openai import OpenAI\nfrom llama_index.core.tools import FunctionTool\nfrom llama_index.core.agent import FunctionCallingAgentWorker\n\n\nimport nest_asyncio\n\nnest_asyncio.apply()\n\n\ndef run_code(lang: str, code: str, libraries: Optional[List] = None) -> str:\n \"\"\"\n Run code in a sandboxed environment.\n :param lang: The language of the code, must be one of ['python', 'java', 'javascript', 'cpp', 'go', 'ruby'].\n :param code: The code to run.\n :param libraries: The libraries to use, it is optional.\n :return: The output of the code.\n \"\"\"\n with SandboxSession(lang=lang, verbose=False) as session: # type: ignore[attr-defined]\n return session.run(code, libraries).text\n\n\nif __name__ == \"__main__\":\n llm = OpenAI(model=\"gpt-4o\", temperature=0)\n code_execution_tool = FunctionTool.from_defaults(fn=run_code)\n\n agent_worker = FunctionCallingAgentWorker.from_tools(\n [code_execution_tool],\n llm=llm,\n verbose=True,\n allow_parallel_tool_calls=False,\n )\n agent = agent_worker.as_agent()\n\n response = agent.chat(\n \"Write python code to calculate Pi number by Monte Carlo method then run it.\"\n )\n print(response)\n\n response = agent.chat(\n \"Write python code to calculate the factorial of a number then run it.\"\n )\n print(response)\n\n response = agent.chat(\n \"Write python code to calculate the Fibonacci sequence then run it.\"\n )\n print(response)\n\n response = agent.chat(\"Calculate the sum of the first 10000 numbers.\")\n print(response)\n```\n\n### Contributing\n\nWe welcome contributions to improve sysbox! Since I am a Python developer, I am not familiar with other languages. If you are interested in adding better support for other languages, please feel free to submit a pull request.\n\nHere is a list of things you can do to contribute:\n- [ ] Add Java maven support.\n- [x] Add support for JavaScript.\n- [x] Add support for C++.\n- [x] Add support for Go.\n- [ ] Add support for Ruby.\n- [x] Add remote Docker host support.\n- [x] Add remote Kubernetes cluster support.\n- [x] Langchain integration.\n- [x] LlamaIndex integration.\n- [ ] Commit the last container state to the image before closing kubernetes session.\n\n### License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n",
"bugtrack_url": null,
"license": null,
"summary": "Lightweight and portable sandbox runtime (code interpreter) Python library",
"version": "0.1.2",
"project_urls": {
"Homepage": "https://github.com/vndee/sysbox"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "51ea641216921cb41a021930766537cfd7f55ff1c0b8d0a5e5ab195f86403f3c",
"md5": "ba5b49cb1b0296759c6544ec34d8a6db",
"sha256": "39189909a68351d29bf35e5f74cb943b3abe9ee525891a25121f4321a71dd61f"
},
"downloads": -1,
"filename": "sysbox-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ba5b49cb1b0296759c6544ec34d8a6db",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 14087,
"upload_time": "2024-09-01T20:33:03",
"upload_time_iso_8601": "2024-09-01T20:33:03.788661Z",
"url": "https://files.pythonhosted.org/packages/51/ea/641216921cb41a021930766537cfd7f55ff1c0b8d0a5e5ab195f86403f3c/sysbox-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "182c5a3ca97c69af829e791d04b3690710802a7ed236bdb9944584eb2e731137",
"md5": "a2beb06e3ba7e9569eee9fcc47356d76",
"sha256": "1787146ab944b1bc2ceb176ff68e3e3b5984c9760f59a3f85a80a6e2521129fd"
},
"downloads": -1,
"filename": "sysbox-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "a2beb06e3ba7e9569eee9fcc47356d76",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 14254,
"upload_time": "2024-09-01T20:33:05",
"upload_time_iso_8601": "2024-09-01T20:33:05.596757Z",
"url": "https://files.pythonhosted.org/packages/18/2c/5a3ca97c69af829e791d04b3690710802a7ed236bdb9944584eb2e731137/sysbox-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-01 20:33:05",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "vndee",
"github_project": "sysbox",
"github_not_found": true,
"lcname": "sysbox"
}
