> ## 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.

# FAQ

> Common questions about Luna Studio — datasets, models, integrations, and more.

If your question isn't answered here, check [Troubleshooting](/luna-studio/ui/reference/troubleshooting) for runtime issues.

## General

<AccordionGroup>
  <Accordion title="What is Luna Studio?">
    Luna Studio is Galileo's web app for **fine-tuning custom evaluation metrics** for LLM applications. You bring a small labelled test set, optionally generate a training set, fine-tune a Luna base model, and register the resulting metric back into the [Galileo metrics store](/concepts/metrics/overview). See [Welcome](/luna-studio/ui/index) for the longer pitch.
  </Accordion>

  <Accordion title="Who is it for?">
    Data scientists, ML engineers, and AI engineers who need evaluation metrics tailored to a specific domain (legal, healthcare, RAG over internal docs, etc.). Use the [Luna Studio UI](/luna-studio/ui/index) for a guided, no-code workflow. Use the [Luna Studio SDK](/luna-studio/sdk/overview) when you want more control or need to run fine-tuning on your own infrastructure.
  </Accordion>

  <Accordion title="How is Luna Studio different from Galileo?">
    Galileo is the broader platform — evaluation, observability, guardrails. Luna Studio is the metric-fine-tuning workspace inside Galileo. Metrics produced in Luna Studio are registered to the Galileo metrics store, where they're usable
    across the rest of the platform.
  </Accordion>

  <Accordion title="How do I get Luna Studio for my org?">
    Luna Studio is part of the enterprise tier of Galileo and is deployed by Galileo into your own cluster or cloud. See [Availability and deployment](/luna-studio/ui/availability), or [contact us](https://galileo.ai/contact-sales) to get started.
  </Accordion>
</AccordionGroup>

## Test sets and training sets

<AccordionGroup>
  <Accordion title="How big should my test set be?">
    Ideally a test should consist of 1000-3000 samples with a good distribution across the classes. We enforce a minimum of 300 human-labelled rows with at least 100 samples per class, since quality is more important than quantity, and human labelling isn't cheap.
  </Accordion>

  <Accordion title="Do I have to upload a training set?">
    Not necessarily. If you have a training set, then sure, but if not, you can choose to generate data using **Generate from test set** — Luna Studio synthetically generates a training set from 20% of your test set. See [Step 3](/luna-studio/ui/runs/new-run/step-3-training-set#generate-from-test-set).

    Upload your own training set when you have labelled production logs that better represent the distribution you want to evaluate.
  </Accordion>

  <Accordion title="Can my training set be unlabelled?">
    Yes, for uploaded or imported logs. Luna Studio labels unlabelled logs with your LLM-as-judge prompt first, saves the labelled result as a training dataset, and then uses that labelled dataset for training. Generated training sets are
    always labelled.
  </Accordion>

  <Accordion title="Can I reuse a test set across multiple projects?">Yes. Datasets are **org-scoped**, not project-scoped. Once you've added a test set, every project in your org can use it.</Accordion>

  <Accordion title="What file formats are supported?">
    Currently we support `.csv` and `.jsonl` formats. See [Add a dataset](/luna-studio/ui/datasets/add-a-dataset#format-reference).
  </Accordion>
</AccordionGroup>

## Metrics

<AccordionGroup>
  <Accordion title="What's the difference between a predefined metric and a custom metric?">
    Predefined metrics use battle-tested LLM-as-judge prompts curated by Galileo (e.g. Toxicity, Context adherence). Custom metrics let you write your own prompt. Both fine-tune the same way.
  </Accordion>

  <Accordion title="What's a 'step' on a metric?">
    The **step** is which part of a Galileo trace the metric runs against: a single LLM call (LLM span), a retrieval step (Retriever), an agent step (Agent span), or a trace-level input. See [Custom prompts in Step
    1](/luna-studio/ui/runs/new-run/step-1-metric#steps-in-detail).
  </Accordion>

  <Accordion title="Can I edit a registered metric?">
    No. Once registered, the metric is snapshotted in the Galileo metrics store. To iterate, launch a new run with the same metric template and register it under a new name (or unregister the old one in Galileo first).
  </Accordion>
</AccordionGroup>

## Training

<AccordionGroup>
  <Accordion title="How long does training take?">Depends on the base model, training set size and GPU availability. Most runs take a few hours, and larger models or larger datasets can take longer.</Accordion>

  <Accordion title="Can I cancel a training run?">
    Not today. Once a run is **Training**, it runs to completion or failure. We're tracking this for a future release.
  </Accordion>
</AccordionGroup>

## Integrations

<AccordionGroup>
  <Accordion title="Which LLM providers does Luna Studio support?">
    Luna Studio supports named hosted providers, Azure, Vertex AI, AWS-hosted models, custom model
    setups, and Galileo. See [Integrations overview](/luna-studio/ui/integrations/overview).
  </Accordion>

  <Accordion title="What's the Custom integration for?">
    For in-house models, OpenAI-compatible proxies, or providers that aren't covered by the named
    integrations. See [Custom models and proxies](/luna-studio/ui/integrations/llm-providers#custom-models-and-proxies).
  </Accordion>
</AccordionGroup>

## Where to go next

<CardGroup cols={2}>
  <Card title="Troubleshooting" icon="bug" href="/luna-studio/ui/reference/troubleshooting">
    Runtime errors and how to recover.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/luna-studio/ui/quickstart">
    End-to-end walkthrough.
  </Card>
</CardGroup>