Quick setup guide¶
Before going further, make sure you have ROS 2 (Jazzy or Humble) installed and sourced on your
system. If you don't have ROS 2 follow the installation documentation for
Humble or
Jazzy. Make sure that
ros-dev-tools
are installed.
Docker images
RAI has experimental docker images. See the docker for instructions.
RAI outside of ROS 2
RAI can be used outside of ROS 2. This means that no ROS 2 related features will be available.
You can still use RAI's core agent framework, tool system, message passing, and integrations such as LangChain, even if ROS 2 is not installed or sourced on your machine. This is useful for:
- Developing and testing AI logic, tools, and workflows independently of any robotics middleware
- Running RAI agents in simulation or cloud environments where ROS 2 is not present
- Using RAI as a generic multimodal agent framework for non-robotic applications
If you later decide to integrate with ROS 2, you can simply install and source ROS 2, and all ROS 2-specific RAI features (such as connectors, aggregators, and tools) will become available automatically.
1. Setting up the workspace:¶
1.1 Install poetry¶
RAI uses Poetry for python packaging and dependency management. Install poetry with the following line:
curl -sSL https://install.python-poetry.org | python3 -
Alternatively, you can opt to do so by following the official docs.
1.2 Clone the repository:¶
git clone https://github.com/RobotecAI/rai.git
cd rai
1.3 Create poetry virtual environment and install dependencies:¶
poetry install
rosdep install --from-paths src --ignore-src -r -y
Additional dependencies
RAI is modular. If you want to use features such as speech-to-speech, simulation and benchmarking suite, openset detection, or NoMaD integration, install additional dependencies:
poetry install --with openset,nomad,s2s,simbench # or `--all-groups` for full setup
Group Name | Description | Dependencies |
---|---|---|
s2s | Speech-to-Speech functionality | rai_asr, rai_tts |
simbench | Simulation and benchmarking tools | rai_sim, rai_bench |
openset | Open-set detection capabilities | groundingdino, groundedsam |
nomad | Visual Navigation - NoMaD integration | visualnav_transformer |
docs | Documentation-related dependencies | mkdocs, mkdocs-material, pymdown-extensions |
1.4 Configure RAI¶
Run the configuration tool to set up your LLM vendor and other settings:
poetry run streamlit run src/rai_core/rai/frontend/configurator.py
Web browser
If the web browser does not open automatically, open the URL displayed in the terminal manually.
2. Build the project:¶
2.1 Build RAI workspace¶
colcon build --symlink-install
2.2 Activate the virtual environment:¶
source ./setup_shell.sh
3. Setting up vendors¶
RAI is vendor-agnostic. Use the configuration in config.toml
to set up your vendor
of choice for RAI modules. Vendor choices for RAI and our recommendations are summarized in
Vendors Overview.
Best-performing AI models
We strongly recommend you to use of best-performing AI models to get the most out of RAI!
Pick your local solution or service provider and follow one of these guides: