Skip to main content

Installation

note

Before proceeding with the installation, ensure you have met the prerequisites.

Follow these steps to install Rubra:

  1. Clone the Rubra GitHub repository by executing the following command in your terminal:

    git clone https://github.com/rubra-ai/rubra.git

  2. Navigate into the rubra directory:

    cd rubra

  3. (Optional) Define the models you want Rubra to access by modifying llm-config.yaml. Refer to LLM Configuration instructions for more details. Additionally, you can add or remove LLMs in the Rubra UI after installation.

  4. Pull the necessary images and start Rubra:

    docker-compose pull  && docker-compose up -d

After completing these steps, Rubra should be successfully installed and running on your local machine.

Access the Rubra UI by visiting http://localhost:8501 in your browser.

Develop with Rubra backend by setting the OpenAI base URL to Rubra backend's URL. By default, Rubra backend runs on http://localhost:8000.

from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/", api_key="abc")