Integrations overview

Documentation Index

Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt

Use this file to discover all available pages before exploring further.

The Integrations page is where you connect the external services Luna Studio needs. Integrations are org-scoped - once added, every project in your org can use them.

​

What integrations are for

Luna Studio works with two kinds of integrations:

• Runtime integrations - connect the services Luna Studio uses while the app is running, such as LLM providers and Galileo.
• Deployment integrations - connect the training platform Luna Studio uses behind the scenes for fine-tuning jobs.

You don’t need every provider — most users start with one (OpenAI or Anthropic) and add more later.

​

Runtime integration types

​

LLM providers

Use an LLM integration when you want Luna Studio to work with a hosted provider, a cloud-managed deployment, or your own internal model endpoint. Supported setups include:

• named providers such as OpenAI, Anthropic, Mistral, and others
• Azure
• Vertex AI
• AWS-hosted models
• Custom models and proxies

For setup guidance, see LLM providers.

​

Galileo

The Galileo integration is a single API key that unlocks platform-level features such as importing datasets from Galileo and registering metrics back to Galileo.

​

Training platforms

Luna Studio also supports training platform integrations for the infrastructure that runs fine-tuning jobs:

• Vertex AI Pipelines
• AzureML Pipelines
• SageMaker Pipelines
• Kubernetes

These are deployment-level integrations, not settings users configure in the Luna Studio UI. The training platform is chosen when Luna Studio is deployed and is fixed for that deployment. See Availability and deployment for how Galileo provisions Luna Studio into your cluster.

​

Where to go next