isopro 0.0.2

Intelligent Simulation Orchestration for Large Language Models

ISOPro: Pro Tools for Intelligent Simulation Orchestration for Large Language Models

ISOPRO is a powerful and flexible Python package designed for creating, managing, and analyzing simulations involving Large Language Models (LLMs). It provides a comprehensive suite of tools for reinforcement learning, conversation simulations, adversarial testing, custom environment creation, and advanced orchestration of multi-agent systems.

Features

• Custom Environment Creation: Easily create and manage custom simulation environments for LLMs. COMING SOON
• Conversation Simulation: Simulate and analyze conversations with AI agents using various user personas. COMING SOON
• Adversarial Testing: Conduct adversarial simulations to test the robustness of LLM-based systems. COMING SOON
• Reinforcement Learning: Implement and experiment with RL algorithms in LLM contexts. COMING SOON
• Utility Functions: Analyze simulation results, calculate LLM metrics, and more.
• Flexible Integration: Works with popular LLM platforms like OpenAI's GPT models, Claude (Anthropic), and Hugging Face models.
• Orchestration Simulation: Manage and execute complex multi-agent simulations with different execution modes. NOW AVAILABLE

Installation

You can install ISOPRO directly from GitHub using pip:

pip install git+https://github.com/iso-ai/isopro.git

Orchestration Simulation

ISOPRO now includes powerful orchestration capabilities for managing complex multi-agent simulations. Here's an example of how to use the orchestration simulation feature:

from isopro.orchestration_simulation.main import OrchestrationEnv, AgentComponent
from isopro.orchestration_simulation.utils import setup_logging
from langchain.agents import create_react_agent
from langchain_openai import OpenAI
from langchain.tools import Tool

# Set up logging
logger = setup_logging(log_file="simulation.log")

# Create tools and agent
tools = [
    Tool(name="Search", func=lambda x: "Search result for " + x, description="Search the web"),
    Tool(name="Calculator", func=lambda x: eval(x), description="Perform calculations")
]
llm = OpenAI(temperature=0)
agent = create_react_agent(llm, tools, "You are a helpful assistant.")

# Create simulation environment
sim_env = SimulationEnvironment()

# Add agent components
for _ in range(3):
    sim_env.add_component(AgentComponent(agent, tools))

# Run simulations in different modes
sequence_results = sim_env.run_simulation(mode='sequence', input_data="What is 2+2 and who was the first person on the moon?")
parallel_results = sim_env.run_simulation(mode='parallel', input_data="Compare the populations of New York and Tokyo.")
node_results = sim_env.run_simulation(mode='node', input_data="Explain the theory of relativity.")

# Log results
logger.info(f"Sequence mode results: {sequence_results}")
logger.info(f"Parallel mode results: {parallel_results}")
logger.info(f"Node mode results: {node_results}")

This example demonstrates how to set up a multi-agent simulation environment, add agent components, and run simulations in different execution modes (sequence, parallel, and node-based).

For more detailed examples, check out the Jupyter notebooks in the examples/ directory.

Documentation

For full documentation, including API references and advanced usage examples, please visit our GitHub Wiki.

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Citation

If you use ISOPRO in your research, please cite it as follows:

@software{isopro2024,
  author = {Jazmia Henry},
  title = {ISOPRO: Intelligent Simulation Orchestration for Large Language Models},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/iso-ai/isopro}}
}

Contact

For questions or support, please open an issue on our GitHub issue tracker.