RIME Enterprise (Local) Installation

The local installation consists of two parts:

The RIME backend and frontend.
- This contains the Docker container infrastructure necessary to process and display test results.
The Python package.
- This contains the command-line interface (CLI) and Python libraries used to run tests on your models and data.

Pre-requisites

Before beginning, please ensure you have the following:

The following system requirements:
- at least 4 GB RAM
- at least 12 GB free disk space
- 3.7 ≤ python ≤ 3.9
- one of the following package managers
  - pip
  - conda
Docker >= 20.10.0
- Linux Users: You will also need to follow these post installation instructions to use Docker without root access.
Docker Compose >= 1.29.0
The rime_trial bundle ( download here )
A token.txt file (will be provided by your RI representative)

Install RIME Backend & Frontend

Set Up Your Environment

To avoid interfering with your other projects’ dependencies, we will create a new Python virtual environment for RIME.

Download ( link here ) and extract (tar -xzf rime-trial-0.16.14.tar.gz) the rime_trial bundle.
Place the token.txt file inside of rime_trial/.
Step into rime_trial/ — this will be our working directory throughout the installation.
Select a virtual environment manager (currently either pip or Conda) and follow the appropriate instructions below.

Pip Installation
1. Create a new python virtual environment.
```
python -m venv rime-venv
```
2. Activate the virtual environment.
  
  macOS & Linux
```
source rime-venv/bin/activate
```
  Windows
```
.\rime-venv\Scripts\activate
```
3. Update pip and install required Python packages from trial_requirements.txt.
```
pip install --upgrade pip
pip install -r trial_requirements.txt
```
Conda Installation
1. Create a new conda virtual environment. Replace $PYTHON_VERSION_YOU_WISH_TO_USE with the version of Python that you wish to use (e.g., 3.8).
```
conda create --name rime-venv python=$PYTHON_VERSION_YOU_WISH_TO_USE
```
2. Activate the virtual environment.
```
conda activate rime-venv
```
3. Update pip and install required Python packages from trial_requirements.txt.
```
pip install --upgrade pip
pip install -r trial_requirements.txt
```

Start RIME Backend & Frontend

NOTE: Running the start command will generate a Robust Intelligence license file and place it in a newly created .robustintelligence folder in your $HOME directory.

Run the rime-helper start command to start the RIME backend and frontend.
```
python rime_helper.py start
```
Wait until you see the following message indicating that the backend and frontend have successfully started and that the UI can be viewed at http://localhost:4000.
```
RIME is available at http://localhost:4000
```

(OPTIONAL) If you are running the Docker containers on a remote instance and would like to use port forwarding to view the UI on your local machine, we recommend using SSH tunneling:

ssh -M -S rime-port-forwarding -fNT -L localhost:4000:localhost:4000 -L localhost:5555:localhost:5555 -L localhost:5001:localhost:5001 -L localhost:5002:localhost:5002 -L localhost:5004:localhost:5004 -L localhost:5012:localhost:5012 user@hostname

To terminate the session, you can run the following:

ssh -S rime-port-forwarding -O exit user@hostname

Stop RIME Backend & Frontend

WARNING: The commands below will permanently delete existing RIME test runs.

To stop RIME, run the following. Note that this command will also delete existing RIME test runs.

python rime_helper.py stop

To completely remove RIME, you can uninstall.

python rime_helper.py uninstall

Install the RIME Python Package

Install the RIME Python package.
```
pip install -r rime_requirements.txt
```

Configure environment variables for use in CLI commands:

macOS & Linux

export RIME_UPLOAD_URL=localhost:5001
export RIME_FIREWALL_URL=localhost:5002
export RIME_DISABLE_TLS=True # Recommended for local uploads only!

Windows

$Env:RIME_UPLOAD_URL = 'localhost:5001'
$Env:RIME_FIREWALL_URL = 'localhost:5002'
$Env:RIME_DISABLE_TLS = 'True # Recommended for local uploads only!

Install the RIME NLP Dependencies (Optional)

To use RIME for stress testing Natural Language Processing models, additional Python dependencies must be installed.

pip install -r nlp_requirements.txt

Install the RIME CV Dependencies (Optional)

To use RIME for stress testing Computer Vision models, additional Python dependencies must be installed.

pip install -r cv_requirements.txt