llm-sandbox

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

Stars: 111

Visit

LLM Sandbox is a lightweight and portable sandbox environment designed to securely execute large language model (LLM) generated code in a safe and isolated manner using Docker containers. It provides an easy-to-use interface for setting up, managing, and executing code in a controlled Docker environment, simplifying the process of running code generated by LLMs. The tool supports multiple programming languages, offers flexibility with predefined Docker images or custom Dockerfiles, and allows scalability with support for Kubernetes and remote Docker hosts.

README:

LLM Sandbox

Securely Execute LLM-Generated Code with Ease

LLM Sandbox 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. This project aims to provide an easy-to-use interface for setting up, managing, and executing code in a controlled Docker 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 Poetry

Ensure you have Poetry installed.
Add the package to your project:

poetry add llm-sandbox

Using pip

Ensure you have pip installed.
Install the package:

pip install llm-sandbox

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:

Initialization: Create a SandboxSession object with the desired configuration.
Open Session: Call the open() method to build/pull the Docker image and start the Docker container.
Run Code: Use the run() method to execute code inside the sandbox. Currently, it supports Python, Java, JavaScript, C++, Go, and Ruby. See examples for more details.
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 LLM Sandbox:

from llm_sandbox 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)

LLM Sandbox also supports copying files between the host and the sandbox:

from llm_sandbox 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.execute_command("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.

You can also use remote Docker host as below:

import docker
from llm_sandbox 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 LLM Sandbox with Langchain:

from typing import Optional, List
from llm_sandbox 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:

from typing import Optional, List
from llm_sandbox 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 LLM Sandbox! 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 file for details.

For Tasks:

Click tags to check more tools for each tasks

run code securely manage docker containers execute code copy files integrate with langchain

For Jobs:

software developer data scientist cybersecurity analyst ai engineer devops engineer

Alternative AI tools for llm-sandbox

Similar Open Source Tools

llm-sandbox

github

: 111

continuous-eval

Open-Source Evaluation for LLM Applications. `continuous-eval` is an open-source package created for granular and holistic evaluation of GenAI application pipelines. It offers modularized evaluation, a comprehensive metric library covering various LLM use cases, the ability to leverage user feedback in evaluation, and synthetic dataset generation for testing pipelines. Users can define their own metrics by extending the Metric class. The tool allows running evaluation on a pipeline defined with modules and corresponding metrics. Additionally, it provides synthetic data generation capabilities to create user interaction data for evaluation or training purposes.

github

: 461

redisvl

Redis Vector Library (RedisVL) is a Python client library for building AI applications on top of Redis. It provides a high-level interface for managing vector indexes, performing vector search, and integrating with popular embedding models and providers. RedisVL is designed to make it easy for developers to build and deploy AI applications that leverage the speed, flexibility, and reliability of Redis.

github

: 158

azure-functions-openai-extension

Azure Functions OpenAI Extension is a project that adds support for OpenAI LLM (GPT-3.5-turbo, GPT-4) bindings in Azure Functions. It provides NuGet packages for various functionalities like text completions, chat completions, assistants, embeddings generators, and semantic search. The project requires .NET 6 SDK or greater, Azure Functions Core Tools v4.x, and specific settings in Azure Function or local settings for development. It offers features like text completions, chat completion, assistants with custom skills, embeddings generators for text relatedness, and semantic search using vector databases. The project also includes examples in C# and Python for different functionalities.

github

: 76

GraphRAG-SDK

Build fast and accurate GenAI applications with GraphRAG SDK, a specialized toolkit for building Graph Retrieval-Augmented Generation (GraphRAG) systems. It integrates knowledge graphs, ontology management, and state-of-the-art LLMs to deliver accurate, efficient, and customizable RAG workflows. The SDK simplifies the development process by automating ontology creation, knowledge graph agent creation, and query handling, enabling users to interact and query their knowledge graphs effectively. It supports multi-agent systems and orchestrates agents specialized in different domains. The SDK is optimized for FalkorDB, ensuring high performance and scalability for large-scale applications. By leveraging knowledge graphs, it enables semantic relationships and ontology-driven queries that go beyond standard vector similarity, enhancing retrieval-augmented generation capabilities.

github

: 215

lollms

LoLLMs Server is a text generation server based on large language models. It provides a Flask-based API for generating text using various pre-trained language models. This server is designed to be easy to install and use, allowing developers to integrate powerful text generation capabilities into their applications.

github

: 282

embodied-agents

Embodied Agents is a toolkit for integrating large multi-modal models into existing robot stacks with just a few lines of code. It provides consistency, reliability, scalability, and is configurable to any observation and action space. The toolkit is designed to reduce complexities involved in setting up inference endpoints, converting between different model formats, and collecting/storing datasets. It aims to facilitate data collection and sharing among roboticists by providing Python-first abstractions that are modular, extensible, and applicable to a wide range of tasks. The toolkit supports asynchronous and remote thread-safe agent execution for maximal responsiveness and scalability, and is compatible with various APIs like HuggingFace Spaces, Datasets, Gymnasium Spaces, Ollama, and OpenAI. It also offers automatic dataset recording and optional uploads to the HuggingFace hub.

github

: 158

LightRAG

LightRAG is a PyTorch library designed for building and optimizing Retriever-Agent-Generator (RAG) pipelines. It follows principles of simplicity, quality, and optimization, offering developers maximum customizability with minimal abstraction. The library includes components for model interaction, output parsing, and structured data generation. LightRAG facilitates tasks like providing explanations and examples for concepts through a question-answering pipeline.

github

: 562

IntelliNode

IntelliNode is a javascript module that integrates cutting-edge AI models like ChatGPT, LLaMA, WaveNet, Gemini, and Stable diffusion into projects. It offers functions for generating text, speech, and images, as well as semantic search, multi-model evaluation, and chatbot capabilities. The module provides a wrapper layer for low-level model access, a controller layer for unified input handling, and a function layer for abstract functionality tailored to various use cases.

github

: 201

swarmgo

SwarmGo is a Go package designed to create AI agents capable of interacting, coordinating, and executing tasks. It focuses on lightweight agent coordination and execution, offering powerful primitives like Agents and handoffs. SwarmGo enables building scalable solutions with rich dynamics between tools and networks of agents, all while keeping the learning curve low. It supports features like memory management, streaming support, concurrent agent execution, LLM interface, and structured workflows for organizing and coordinating multiple agents.

github

: 164

StepWise

StepWise is a code-first, event-driven workflow framework for .NET designed to help users build complex workflows in a simple and efficient way. It allows users to define workflows using C# code, visualize and execute workflows from a browser, execute steps in parallel, and resolve dependencies automatically. StepWise also features an AI assistant called `Geeno` in its WebUI to help users run and analyze workflows with ease.

github

: 99

flow-prompt

Flow Prompt is a dynamic library for managing and optimizing prompts for large language models. It facilitates budget-aware operations, dynamic data integration, and efficient load distribution. Features include CI/CD testing, dynamic prompt development, multi-model support, real-time insights, and prompt testing and evolution.

github

: 68

cappr

CAPPr is a tool for text classification that does not require training or post-processing. It allows users to have their language models pick from a list of choices or compute the probability of a completion given a prompt. The tool aims to help users get more out of open source language models by simplifying the text classification process. CAPPr can be used with GGUF models, Hugging Face models, models from the OpenAI API, and for tasks like caching instructions, extracting final answers from step-by-step completions, and running predictions in batches with different sets of completions.

github

: 64

hydraai

Generate React components on-the-fly at runtime using AI. Register your components, and let Hydra choose when to show them in your App. Hydra development is still early, and patterns for different types of components and apps are still being developed. Join the discord to chat with the developers. Expects to be used in a NextJS project. Components that have function props do not work.

github

: 90

videokit

VideoKit is a full-featured user-generated content solution for Unity Engine, enabling video recording, camera streaming, microphone streaming, social sharing, and conversational interfaces. It is cross-platform, with C# source code available for inspection. Users can share media, save to camera roll, pick from camera roll, stream camera preview, record videos, remove background, caption audio, and convert text commands. VideoKit requires Unity 2022.3+ and supports Android, iOS, macOS, Windows, and WebGL platforms.

github

: 114

langchaingo

LangChain Go is a Go language implementation of LangChain, a framework for building applications with LLMs through composability. It provides a simple and easy-to-use API for interacting with LLMs, making it easy to add language-based features to your applications.

github

: 5.3k

For similar tasks

llm-sandbox

github

: 111

agentscope

AgentScope is a multi-agent platform designed to empower developers to build multi-agent applications with large-scale models. It features three high-level capabilities: Easy-to-Use, High Robustness, and Actor-Based Distribution. AgentScope provides a list of `ModelWrapper` to support both local model services and third-party model APIs, including OpenAI API, DashScope API, Gemini API, and ollama. It also enables developers to rapidly deploy local model services using libraries such as ollama (CPU inference), Flask + Transformers, Flask + ModelScope, FastChat, and vllm. AgentScope supports various services, including Web Search, Data Query, Retrieval, Code Execution, File Operation, and Text Processing. Example applications include Conversation, Game, and Distribution. AgentScope is released under Apache License 2.0 and welcomes contributions.

github

: 5.8k

dwata

Dwata is a desktop application that allows users to chat with any AI model and gain insights from their data. Chats are organized into threads, similar to Discord, with each thread connecting to a different AI model. Dwata can connect to databases, APIs (such as Stripe), or CSV files and send structured data as prompts when needed. The AI's response will often include SQL or Python code, which can be used to extract the desired insights. Dwata can validate AI-generated SQL to ensure that the tables and columns referenced are correct and can execute queries against the database from within the application. Python code (typically using Pandas) can also be executed from within Dwata, although this feature is still in development. Dwata supports a range of AI models, including OpenAI's GPT-4, GPT-4 Turbo, and GPT-3.5 Turbo; Groq's LLaMA2-70b and Mixtral-8x7b; Phind's Phind-34B and Phind-70B; Anthropic's Claude; and Ollama's Llama 2, Mistral, and Phi-2 Gemma. Dwata can compare chats from different models, allowing users to see the responses of multiple models to the same prompts. Dwata can connect to various data sources, including databases (PostgreSQL, MySQL, MongoDB), SaaS products (Stripe, Shopify), CSV files/folders, and email (IMAP). The desktop application does not collect any private or business data without the user's explicit consent.

github

: 121

Tiger

Tiger is a community-driven project developing a reusable and integrated tool ecosystem for LLM Agent Revolution. It utilizes Upsonic for isolated tool storage, profiling, and automatic document generation. With Tiger, you can create a customized environment for your agents or leverage the robust and publicly maintained Tiger curated by the community itself.

github

: 365

SWE-agent

SWE-agent is a tool that turns language models (e.g. GPT-4) into software engineering agents capable of fixing bugs and issues in real GitHub repositories. It achieves state-of-the-art performance on the full test set by resolving 12.29% of issues. The tool is built and maintained by researchers from Princeton University. SWE-agent provides a command line tool and a graphical web interface for developers to interact with. It introduces an Agent-Computer Interface (ACI) to facilitate browsing, viewing, editing, and executing code files within repositories. The tool includes features such as a linter for syntax checking, a specialized file viewer, and a full-directory string searching command to enhance the agent's capabilities. SWE-agent aims to improve prompt engineering and ACI design to enhance the performance of language models in software engineering tasks.

github

: 13.4k

NeoGPT

NeoGPT is an AI assistant that transforms your local workspace into a powerhouse of productivity from your CLI. With features like code interpretation, multi-RAG support, vision models, and LLM integration, NeoGPT redefines how you work and create. It supports executing code seamlessly, multiple RAG techniques, vision models, and interacting with various language models. Users can run the CLI to start using NeoGPT and access features like Code Interpreter, building vector database, running Streamlit UI, and changing LLM models. The tool also offers magic commands for chat sessions, such as resetting chat history, saving conversations, exporting settings, and more. Join the NeoGPT community to experience a new era of efficiency and contribute to its evolution.

github

: 64

Phi-3-Vision-MLX

Phi-3-MLX is a versatile AI framework that leverages both the Phi-3-Vision multimodal model and the Phi-3-Mini-128K language model optimized for Apple Silicon using the MLX framework. It provides an easy-to-use interface for a wide range of AI tasks, from advanced text generation to visual question answering and code execution. The project features support for batched generation, flexible agent system, custom toolchains, model quantization, LoRA fine-tuning capabilities, and API integration for extended functionality.

github

: 186

langchain-extract

LangChain Extract is a simple web server that allows you to extract information from text and files using LLMs. It is built using FastAPI, LangChain, and Postgresql. The backend closely follows the extraction use-case documentation and provides a reference implementation of an app that helps to do extraction over data using LLMs. This repository is meant to be a starting point for building your own extraction application which may have slightly different requirements or use cases.

github

: 916

For similar jobs

sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github

: 7.1k

teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github

: 390

ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github

: 159

classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github

: 593

chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github

: 27.7k

BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github

: 953

uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github

: 1.2k

griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github

: 2.1k