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

# Connections

> Connect and sync data from third-party applications and databases into your knowledge base.

The **Connections** tab allows you to connect external data sources to your knowledge base. Connected sources are automatically indexed so your agents can search and retrieve content without copying data into the platform.

Connectors are organized into four categories: **Cloud Storage & Documentation**, **Databases**, **Business Applications**, and **Cloud Platforms**.

## Cloud Storage & Documentation

<CardGroup cols={3}>
  <Card title="Google Drive" icon="google-drive" href="/project-settings/kb-settings/kb-connections/kb-google-drive">
    Link Drive so agents can search Docs, Sheets, and files you allow. Content is indexed into the knowledge base; originals stay in Google.
  </Card>

  <Card title="Microsoft SharePoint" icon="microsoft" href="/project-settings/kb-settings/kb-connections/kb-sharepoint">
    Connect SharePoint Online sites and document libraries. Team files become searchable without copying them out of M365.
  </Card>

  <Card title="Confluence" icon="confluence" href="/project-settings/kb-settings/kb-connections/kb-confluence">
    Sync spaces and pages from Confluence Cloud or Data Center. Wikis, specs, and runbooks stay available to your project AI.
  </Card>

  <Card title="Zoomin" icon="book" href="/project-settings/kb-settings/kb-connections/kb-zoomin">
    Ingest structured product documentation from Zoomin. Ideal for manuals, release notes, and technical publications.
  </Card>
</CardGroup>

## Databases

<CardGroup cols={3}>
  <Card title="MySQL" icon="database" href="/project-settings/kb-settings/kb-connections/kb-my-sql">
    Attach MySQL or MariaDB with host, database, and credentials. Choose tables or views to index for grounded answers.
  </Card>

  <Card title="Microsoft SQL" icon="microsoft" href="/project-settings/kb-settings/kb-connections/kb-microsoft-sql">
    Connect SQL Server on-premises or on Azure SQL. Index only the schemas and objects you authorize for search.
  </Card>

  <Card title="Oracle" icon="database" href="/project-settings/kb-settings/kb-connections/kb-oracle">
    Connect Oracle Database over JDBC with your service account. Bring selected tables into the knowledge base for AI retrieval.
  </Card>

  <Card title="Generic SQL" icon="code" href="/project-settings/kb-settings/kb-connections/kb-generic-sql">
    Use a connection string for Snowflake, Postgres, Redshift, and more. Use when there is no dedicated connector tile for your warehouse.
  </Card>
</CardGroup>

## Business Applications

<CardGroup cols={3}>
  <Card title="Odoo" icon="briefcase" href="/project-settings/kb-settings/kb-connections/kb-odoo">
    Connect Odoo ERP for CRM, inventory, accounting, and more. Expose approved records so agents answer with live business data.
  </Card>
</CardGroup>

## Cloud Platforms

<CardGroup cols={3}>
  <Card title="Google Cloud Platform" icon="google" href="/project-settings/kb-settings/kb-connections/kb-google-cloud-platform">
    Run BigQuery, invoke Cloud Run services and functions, and query Cloud SQL. Authenticated via service-account JSON; share access by adding IAM roles.
  </Card>
</CardGroup>

## Best Practices

### Connector Setup

1. **Use Specific Folders** — Connect specific folders rather than entire accounts.
2. **Set Appropriate Schedules** — Balance content freshness with system load.
3. **Monitor Sync Status** — Regularly check sync success and failures.
4. **Test Connections** — Verify connections work before relying on them in production.

### Security

1. **Use Service Accounts** — Prefer service accounts over personal accounts for stability and security.
2. **Limit Permissions** — Grant only the permissions necessary for indexing.
3. **Regular Audits** — Review connected accounts periodically and remove unused connections.
4. **Secure Credentials** — Never share connection credentials.

### Performance

1. **Selective Sync** — Sync only the content your agents actually need.
2. **Schedule Wisely** — Avoid scheduling syncs during peak usage times.
3. **Monitor Resources** — Watch for performance impacts after enabling new connectors.
4. **Optimize Queries** — For database connectors, use efficient queries to limit the data retrieved.

## Troubleshooting

<AccordionGroup>
  <Accordion title="Connection failures">
    **Problem:** Connector fails to connect.

    **Solutions:**

    1. Verify credentials are correct.
    2. Check network connectivity.
    3. Ensure the required permissions have been granted.
    4. Review connector-specific requirements.
  </Accordion>

  <Accordion title="Sync failures">
    **Problem:** Content is not syncing.

    **Solutions:**

    1. Check sync schedule configuration in the **Sync & Schedule** tab.
    2. Verify the connector is still connected in the **Connections** tab.
    3. Review sync logs for errors.
    4. Try a manual sync using the **Sync Now** button to test the connection.
  </Accordion>

  <Accordion title="Missing content">
    **Problem:** Expected content is not appearing in the Knowledge Base.

    **Solutions:**

    1. Verify the sync completed successfully.
    2. Check folder or query configuration for the connector.
    3. Ensure the content matches the sync criteria and filters.
    4. Review sync filters and settings.
  </Accordion>
</AccordionGroup>