> ## Documentation Index
> Fetch the complete documentation index at: https://dcpma.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# OASIS-LLM: Rate Images with Vision-Language Models

> OASIS-LLM replays the OASIS affective rating procedure using LLMs and compares model valence and arousal ratings to 822 human raters across 900 OASIS images.

OASIS-LLM is a research harness that takes the **Open Affective Standardized Image Set (OASIS)** — 900 color images rated by 822 MTurk workers on 7-point valence and arousal scales — and replays the same rating procedure against modern vision-language models. You get a reproducible pipeline for running LLM rating experiments and an interactive dashboard to compare model output against established human norms.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Install OASIS-LLM and launch your first pilot run in minutes.
  </Card>

  <Card title="Experiment Design" icon="flask" href="/experiment-design">
    Understand the OASIS procedure, rating scales, and how trials are structured.
  </Card>

  <Card title="Configuration" icon="sliders" href="/configuration">
    Every RunConfig field: providers, models, sampling, prompts, and run identity.
  </Card>

  <Card title="Analysis" icon="chart-line" href="/analysis-vs-human">
    Compare LLM ratings to human norms using the dashboard's statistical tools.
  </Card>

  <Card title="Cost & Latency" icon="dollar-sign" href="/cost-latency">
    Real pilot numbers and full-set extrapolations to budget your runs.
  </Card>

  <Card title="Glossary" icon="book" href="/glossary">
    Definitions for valence, arousal, ICC, canonical hash, and more.
  </Card>
</CardGroup>

## What OASIS-LLM does

OASIS-LLM lets you ask: **how do contemporary LLMs rate the emotional content of images?** You configure a run with a YAML file, point it at a model, and the harness submits each image to the model with the paper-verbatim valence or arousal instructions. Results are stored in a local DuckDB database. A Streamlit dashboard lets you browse runs, explore individual images, and run statistical comparisons against the human norms from Kurdi, Lozano, & Banaji (2017).

<Steps>
  <Step title="Install and configure">
    Install with `uv sync`, copy `.env.example` to `.env`, and add your provider API key.
  </Step>

  <Step title="Launch the dashboard">
    Run `uv run oasis-llm dashboard` to open the Streamlit UI at `http://localhost:8501`.
  </Step>

  <Step title="Define an experiment">
    Create a YAML config selecting your model, image set, and sampling parameters.
  </Step>

  <Step title="Run and analyze">
    Execute the run via CLI or dashboard, then open the Analysis page to compare against human norms.
  </Step>
</Steps>

## Supported providers

OASIS-LLM routes all model calls through [LiteLLM](https://docs.litellm.ai/), giving you a single interface across providers:

* **OpenRouter** — access to hundreds of open and closed models with cost tracking
* **OpenAI** — GPT-4o and other vision models
* **Anthropic** — Claude vision models
* **Google** — Gemini vision models
* **Ollama** — local models running on your own hardware

<Note>
  The 900 OASIS images are licensed under **CC BY-NC-SA 4.0** by the original authors and are not bundled with this tool. Download them from [osf.io/6pnd7](https://osf.io/6pnd7) and unpack into `OASIS/images/`.
</Note>