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

# Global Datastores

> Pre-built datastores available to all users for testing and demos

## Overview

When you create a new Contextual AI account, you automatically have access to several **global datastores**—pre-built knowledge bases you can use immediately to test agents, run demos, or explore the platform without uploading your own documents.

These datastores are read-only and available to all users.

## Available Global Datastores

<CardGroup cols={2}>
  <Card title="Materials Science Research Papers" icon="atom">
    7,546 docs · 41.3 GB
  </Card>

  <Card title="Star Wars Wookiepedia" icon="jedi">
    497 docs · 4.8 GB
  </Card>

  <Card title="Rocket Science" icon="rocket">
    7 docs · 59.1 MB
  </Card>

  <Card title="RFC Library" icon="file-code">
    1,786 docs · 50.7 MB
  </Card>

  <Card title="Raspberry Pi Docs" icon="microchip">
    54 docs · 82 MB
  </Card>
</CardGroup>

## Using Global Datastores

### In the Platform UI

1. Go to **Datastores** in the left navigation
2. Global datastores are marked with a **Demo** badge
3. When creating an agent, select any global datastore from the dropdown

### In Agent Composer YAML

Reference a global datastore by its ID in your YAML configuration:

```yaml theme={null}
nodes:
  search:
    type: SearchStep
    config:
      datastores:
        - <your-datastore-id>
    input_mapping:
      query: __inputs__#query
```

### Via API

Use the datastore ID when creating or configuring agents:

```shell theme={null}
curl --request POST \
  --url https://api.contextual.ai/v1/agents \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "name": "My Demo Agent",
  "datastore_ids": ["78f6bb93-04a5-4883-95f4-d681da6eee23"]
}'
```

## Example Agents

See these demos built on global datastores:

* [Raspberry Pi Agent](/examples/raspberry-pi-agent) — Technical support and troubleshooting for Raspberry Pi hardware
* [Rocket Science Agent](/examples/rocket_science) — Root cause analysis for rocket engine anomalies
* [Material Science Agent](/examples/material-science-agent) — Research assistant using arXiv materials papers; explains in ELI5 style
* [Test Program Generation](/examples/test-automation) — Generate OpenTAP test programs and instrument drivers