Welcome to the exciting world of RAI, a flexible AI agent framework designed to bring advanced Gen AI features to your robots. As RAI is currently in its beta phase, it promises a thrilling journey filled with opportunities for early contributors. This blog post will guide you through the setup process, usage examples, troubleshooting tips, and the exciting features you can leverage in this innovation. Let’s dive in!
Overview of RAI
RAI is designed to:
- Enable a general multi-agent system for robots.
- Add human interactivity and flexibility to problem-solving.
- Support various data types with first-class multi-modality.
- Implement an advanced database for persistent memory.
- Utilize tools oriented towards ROS 2.
- Oversee a comprehensive task and mission orchestrator.
Features
Some of the standout features include:
- Voice interaction (both ways).
- Customizable robot identity and ethical guidelines.
- Integration with advanced tools like LangChain.
- Natural language processing for task management.
- Dynamic listing of interfaces and message types.
Setting Up RAI
Your journey with RAI begins with the initial setup, outlined in these easy steps:
1. Setting up the Workspace
1.1 Install Poetry
Follow the command below to install Poetry (1.8+):
bash
curl -sSL https://install.python-poetry.org | python3 -
Alternatively, you can refer to the official docs.
1.2 Clone the Repository
bash
git clone https://github.com/RobotecAI/rai.git
cd rai
1.3 Create Virtual Environment and Install Dependencies
bash
poetry install
rosdep install --from-paths src --ignore-src -r -y
2. Build the Project
2.1 Build RAI Workspace
bash
colcon build --symlink-install
2.2 Activate Virtual Environment
bash
source .setup_shell.sh
3. Setting up Vendors
You can configure your vendor of choice via the config.toml file. Some RAI modules are still hardcoded to OpenAI models; an effort is underway to change this.
If you don’t have a vendor key, refer to these links:
Congratulations, your installation is now complete!
Running RAI
Once you have set up RAI, you can start running some examples:
- Hello RAI: Interact using a Streamlit chat interface.
- O3DE Husarion ROSbot XL Demo: It allows you to control the robot through natural language commands.
Hello RAI
Run the following command to initiate the chat:
bash
streamlit run src/rai_hmi/rai_hmi_streamlit_hmi_node.py
Remember to execute this command in a sourced shell.
O3DE Rosbot XL Demo
This demo lets you interact with a virtual Husarion ROSbot XL within a simulated environment. It’s a fantastic way to test different commands and see the potential of the framework.
For detailed steps on the demo, check out this guide: husarion-rosbot-xl-demo.
What’s Next?
Once you’re comfortable with RAI, take on these challenges:
- Run RAI on your robot and interact via documentation queries.
- Implement additional tools in your interactions.
- Attempt complex, multi-step tasks for your robot.
Look out for new demos spanning various domains!
Troubleshooting Tips
If you experience issues during setup or usage, consider the following:
- Ensure that all dependencies are installed correctly.
- If you encounter permission issues, try running your terminal as an administrator.
- Make sure that you are using the correct Python version as indicated in the setup requirements.
- You can also reach out to the community via the RAI Q&A.
For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.
Final Thoughts
At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.