Skip to main content
Version: v2.4.0

Quick Start

The AI Optimizer can be installed on a developer's desktop, an on-premises data center, or a cloud environment. It can be run either on bare-metal, within a container, or in a Kubernetes cluster using a Helm chart.

Prefer a Step-by-Step?

The Walkthrough is a great way to install and familiarize yourself with the AI Optimizer and its features in a containerized, development environment.

Prerequisites​

  • uv (for running bare-metal)
  • A container runtime, such as Docker or Podman (for running in a container)
  • Access to a chat model and an embedding model for RAG:
    • API Keys for Third-Party Models
    • On-Premises Models*
  • Oracle AI Database incl. Oracle AI Database Free
*Oracle recommends running on-premises models on hardware with GPUs.
What do I actually need?

The AI Optimizer will start without any AI model or database configured. However:

  • To interact with language models, you will need to configure and enable a chat model.
  • To persist settings across restarts and to enable features like RAG, NL2SQL and the Testbed, a database is required.

Deployment Options​

Available deployment options:

Bare-Metal Installation​

The server and all-in-one installations support Python 3.11 and 3.12.

To run the AI Optimizer on bare-metal:

  1. Download and extract the latest release into a new directory:

    Latest Release: TAR.GZ archive

    For example:

    curl -LO https://github.com/oracle/ai-optimizer/releases/latest/download/ai-optimizer-src.tar.gz
    mkdir ai-optimizer
    tar zxf ai-optimizer-src.tar.gz -C ai-optimizer

    cd ai-optimizer

  2. Create the project environment and install the application:

    uv sync --all-extras

  3. (Optional) Create an environment file to pre-configure the application:

    cp src/.env.example src/.env.dev

    Edit src/.env.dev as needed. See Environment Variables for details.

  4. Start the application:

    uv run python src/entrypoint.py client

  5. Navigate to http://localhost:8501.

  6. Configure the AI Optimizer.

Container Installation​

To run the AI Optimizer in a container:

Same... but different!

The commands in this section work in a macOS/Linux shell or PowerShell 7. The documentation will reference podman commands. If applicable to your environment, podman can be substituted with docker.

If you are using docker, consider aliasing the podman command for convenience:

alias podman=docker

  1. Download and extract the latest release into a new directory:

    Latest Release: TAR.GZ archive

    For example:

    curl -LO https://github.com/oracle/ai-optimizer/releases/latest/download/ai-optimizer-src.tar.gz
    mkdir ai-optimizer
    tar zxf ai-optimizer-src.tar.gz -C ai-optimizer

    cd ai-optimizer

  2. Build the container image.

    note

    macOS Silicon users may need to specify --arch amd64

    podman build -f src/Dockerfile -t localhost/ai-optimizer-aio:latest .

  1. Start the Container:

    podman run -p 8501:8501 -it --rm localhost/ai-optimizer-aio:latest

  2. Navigate to http://localhost:8501.

  3. Configure the AI Optimizer.

Oracle Cloud Infrastructure​

The AI Optimizer can easily be deployed using Infrastructure as Code (IaC) into Oracle Cloud Infrastructure (OCI).

OCI deployment options include:

  • An Always-Free Installation
  • Simple Virtual Machine Installation
  • Advanced Oracle Kubernetes Engine

To get started, review the IaC documentation.

Kubernetes​

The AI Optimizer can be deployed into a Kubernetes cluster using a Helm chart. For more information, see Kubernetes / Helm.