Getting Started - curlyphries/Crew.AI-Ollama-Multi-Agent-System GitHub Wiki

Startup Guide

= Crew.AI Startup Guide =

Welcome to the Crew.AI multi-agent system! Follow this guide to set up and run the application.

== Prerequisites ==
Before starting, ensure you have the following installed:
* Python 3.9 or higher
* Docker (optional but recommended)
* Git

Install the required Python libraries using `pip`:
```shell
pip install -r requirements.txt

== File Structure == The project is organized as follows:

crew-ai/
├── src/
│   ├── main.py                      # Application entry point
│   ├── core/                        # Core functionality
│   │   ├── __init__.py
│   │   ├── orchestrator.py
│   │   ├── memory.py
│   │   └── utils.py
│   ├── agents/                      # Specialized agents
│   │   ├── __init__.py
│   │   ├── ollama_agent.py
│   │   ├── search_agent.py
│   │   └── base_agent.py
│   └── settings/                    # Configuration files
│       ├── config.yaml              # Multi-agent configuration
│       ├── secrets.env              # Environment variables
│       └── logging.yaml             # Logging configuration
├── scripts/                         # Helper scripts
├── tests/                           # Test suites
├── docs/                            # Documentation
└── requirements.txt                 # Python dependencies

== Configuration ==

  1. Update the configuration files in src/settings/:

    • logging.yaml: Set the logging level and format.
    • secrets.env: Add your environment variables (e.g., API keys).

  2. Verify the path for logging.yaml in src/settings/logging_yaml_path.py:

LOGGING_YAML_PATH = "./src/settings/logging.yaml"

== Running the Application ==

  1. Start the application using Python:
python src/main.py
  1. You should see a response from the agents:
Search Agent Response: Search Agent found results for: Latest AI News

== Using Docker ==

  1. Build the Docker image:
docker build -t crew-ai .
  1. Run the Docker container:
docker run --rm -it crew-ai

== Testing == To run tests, use the following commands:

  • Unit tests:
pytest tests/unit/
  • Integration tests:
pytest tests/integration/
  • End-to-End tests:
pytest tests/e2e/

== Troubleshooting ==

  • If you encounter issues with logging, check the logging.yaml file for misconfigurations.
  • For agent-specific errors, inspect the implementations in src/agents/.

== Contributing == We welcome contributions! To contribute:

  1. Fork the repository.
  2. Create a new branch for your feature or fix.
  3. Submit a pull request with a detailed description.

== License == This project is licensed under the terms specified in the LICENSE file.

== Contact == For questions or support, reach out to the development team at: