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

# Run the Google Drive Connector Externally

> Use YAML to configure Google Drive ingestion, enabling structured metadata extraction for files, folders, and Google Sheets.

export const CodePanel = ({children, fileName = 'config.yaml', showLineNumbers = false}) => {
  const codePanelRef = useRef(null);
  const codeContentRef = useRef(null);
  const isProgrammaticScroll = useRef(false);
  const hoverTimeout = useRef(null);
  useEffect(() => {
    let tries = 0;
    const wrapLines = () => {
      const root = codeContentRef.current;
      if (!root) return;
      const pres = Array.from(root.querySelectorAll('pre'));
      if (!pres.length) {
        if (tries++ < 20) requestAnimationFrame(wrapLines);
        return;
      }
      let globalLine = 1;
      pres.forEach(pre => {
        const code = pre.querySelector('code') || pre;
        if (!code || code.dataset.wrapped === 'true') return;
        const raw = code.textContent || '';
        let lines = raw.split('\n');
        while (lines[0] === '') lines.shift();
        while (lines[lines.length - 1] === '') lines.pop();
        code.innerHTML = lines.map(line => {
          const ln = globalLine++;
          const num = showLineNumbers ? `<span class="line-number">${ln}</span>` : '';
          const safe = line.replace(/</g, '&lt;').replace(/>/g, '&gt;') || ' ';
          return `<span class="code-line" data-line="${ln}">${num}${safe}</span>`;
        }).join('');
        code.dataset.wrapped = 'true';
      });
    };
    wrapLines();
  }, [children, showLineNumbers]);
  useEffect(() => {
    const panel = codePanelRef.current;
    const content = codeContentRef.current;
    if (!panel || !content) return;
    const waitForLines = () => {
      const codeLines = content.querySelectorAll('.code-line');
      if (!codeLines.length) {
        requestAnimationFrame(waitForLines);
        return;
      }
      setupHighlighting(codeLines);
    };
    const setupHighlighting = codeLines => {
      const layout = panel.closest('.split-layout');
      const sections = layout.querySelectorAll('.content-section');
      const parseLines = str => {
        if (!str) return [];
        const out = [];
        str.split(',').forEach(p => {
          if (p.includes('-')) {
            const [s, e] = p.split('-').map(Number);
            for (let i = s; i <= e; i++) out.push(i);
          } else {
            const n = Number(p);
            if (!isNaN(n)) out.push(n);
          }
        });
        return out;
      };
      const clearHighlight = () => {
        codeLines.forEach(l => l.classList.remove('highlighted'));
      };
      const highlight = lines => {
        clearHighlight();
        lines.forEach(n => {
          const el = content.querySelector(`.code-line[data-line="${n}"]`);
          if (el) el.classList.add('highlighted');
        });
      };
      const scrollToLines = lines => {
        if (!lines.length) return;
        const first = lines[0];
        const targetLine = lines.length > 1 ? first : lines[0];
        const el = content.querySelector(`.code-line[data-line="${targetLine}"]`);
        if (!el) return;
        isProgrammaticScroll.current = true;
        const containerRect = content.getBoundingClientRect();
        const elRect = el.getBoundingClientRect();
        const offset = elRect.top - containerRect.top + content.scrollTop;
        const TOP_PADDING = 16;
        content.scrollTo({
          top: Math.max(offset - TOP_PADDING, 0),
          behavior: 'smooth'
        });
        setTimeout(() => {
          isProgrammaticScroll.current = false;
        }, 200);
      };
      const activate = (section, scroll) => {
        if (section.classList.contains('active')) return;
        sections.forEach(s => s.classList.remove('active'));
        section.classList.add('active');
        const lines = parseLines(section.dataset.lines);
        highlight(lines);
        if (scroll) scrollToLines(lines);
      };
      const observer = new IntersectionObserver(entries => {
        if (isProgrammaticScroll.current) return;
        entries.forEach(e => {
          if (e.isIntersecting) activate(e.target, false);
        });
      }, {
        threshold: 0.3,
        rootMargin: '-80px 0px -40% 0px'
      });
      sections.forEach(section => {
        observer.observe(section);
        section.addEventListener('click', () => activate(section, true));
        section.addEventListener('mouseenter', () => {
          clearTimeout(hoverTimeout.current);
          hoverTimeout.current = setTimeout(() => activate(section, true), 80);
        });
      });
      if (sections[0]) activate(sections[0], false);
    };
    waitForLines();
  }, []);
  const handleCopy = e => {
    const btn = e.currentTarget;
    const codeLines = codeContentRef.current?.querySelectorAll('.code-line');
    if (!codeLines || codeLines.length === 0) return;
    const text = Array.from(codeLines).map(line => {
      const clone = line.cloneNode(true);
      const lineNumber = clone.querySelector('.line-number');
      if (lineNumber) lineNumber.remove();
      return clone.textContent;
    }).join('\n');
    if (!text) return;
    navigator.clipboard.writeText(text).then(() => {
      btn.dataset.copied = 'true';
      setTimeout(() => btn.dataset.copied = 'false', 1500);
    });
  };
  return <div className="code-panel" ref={codePanelRef}>
      <div className="code-header">
        {fileName}
        <button className="copy-btn" aria-label="Copy full code" data-copied="false" onClick={handleCopy}>
          <svg className="icon-copy" viewBox="0 0 15 16" fill="currentColor">
            <path d="M10.113 3.124H2.205C1.463 3.124.86 3.655.86 4.31v10.005c0 .654.603 1.186 1.345 1.186h7.908c.742 0 1.345-.532 1.345-1.186V4.31c0-.655-.606-1.186-1.345-1.186Z" />
            <path d="M13.138.5H5.229c-.742 0-1.344.531-1.344 1.186 0 .23.209.414.47.414s.47-.184.47-.414c0-.197.182-.357.404-.357h7.909c.223 0 .404.16.404.357V11.69c0 .196-.181.356-.404.356-.262 0-.47.184-.47.415 0 .23.208.415.47.415.742 0 1.344-.532 1.344-1.186V1.686C14.482 1.03 13.88.5 13.138.5Z" />
          </svg>

          <svg className="icon-check" viewBox="0 0 20 20" fill="currentColor">
            <path fillRule="evenodd" d="M16.707 5.293a1 1 0 010 1.414l-7.25 7.25a1 1 0 01-1.414 0l-3.25-3.25a1 1 0 011.414-1.414l2.543 2.543 6.543-6.543a1 1 0 011.414 0z" clipRule="evenodd" />
          </svg>
        </button>
      </div>

      <div className="code-content" ref={codeContentRef}>
        {children}
      </div>
    </div>;
};

export const ContentSection = ({id, title, lines, children}) => <div className="content-section" data-content-id={id} data-lines={lines}>
    {title && <h4>{title}</h4>}
    {children}
  </div>;

export const ContentPanel = ({children}) => <div className="content-panel">{children}</div>;

export const CodePreview = ({children}) => {
  const [instanceId] = useState(() => `preview-${Math.random().toString(36).slice(2)}`);
  useEffect(() => {
    const nav = document.querySelector('nav') || document.querySelector('header') || document.querySelector('[class*="nav"]');
    if (nav) {
      document.documentElement.style.setProperty('--navbar-height', `${nav.offsetHeight}px`);
    }
  }, []);
  return <div className="split-layout" data-preview-id={instanceId}>
      {children}
    </div>;
};

export const ConnectorDetailsHeader = ({name, icon, stage, availableFeatures, unavailableFeatures = [], availableFeaturesCollate = []}) => {
  const showSubHeading = availableFeatures?.length > 0 || unavailableFeatures?.length > 0 || availableFeaturesCollate?.length > 0;
  const totalAvailableFeatures = [...availableFeatures || [], ...availableFeaturesCollate || []];
  return <div className="container">
      <div className="Heading">
        <div className="flex items-center gap-3">
          {icon && <div className="IconContainer">
              <img src={icon} alt={name} noZoom className="ConnectorIcon" />
            </div>}
          <h1 className="ConnectorName">{name}</h1>
          <span className={`StageBadge ${stage === 'PROD' ? 'prod' : 'beta'}`}>
            {stage}
          </span>
        </div>
      </div>
      {showSubHeading && <div className="SubHeading">
          <div className="FeaturesHeading">Feature List</div>
          <div className="FeaturesList">
            {totalAvailableFeatures.map(feature => <div className="FeatureTag AvailableFeature" key={feature}>
                ✓ {feature}
              </div>)}
            {unavailableFeatures.map(feature => <div className="FeatureTag UnavailableFeature" key={feature}>
                ✕ {feature}
              </div>)}
          </div>
        </div>}
    </div>;
};

<ConnectorDetailsHeader icon="/public/images/connectors/googledrive.webp" name="Google Drive" stage="BETA" availableFeatures={["Metadata", "Owners", "Sample Data"]} unavailableFeatures={["Query Usage", "Lineage", "Column-level Lineage", "Data Profiler", "Data Quality", "Tags"]} />

In this section, we provide guides and references to use the Google Drive connector.
Configure and schedule Google Drive metadata workflows from the OpenMetadata UI:

* [Requirements](#requirements)
* [Metadata Ingestion](#metadata-ingestion)

## How to Run the Connector Externally

To run the Ingestion via the UI you'll need to use the OpenMetadata Ingestion Container, which comes shipped with
custom Airflow plugins to handle the workflow deployment.

If, instead, you want to manage your workflows externally on your preferred orchestrator, you can check
the following docs to run the Ingestion Framework **anywhere**.

<Columns cols={2}>
  <Card title="External Schedulers" href="/v2.0.x-SNAPSHOT/deployment/ingestion">
    Get more information about running the Ingestion Framework Externally
  </Card>
</Columns>

## Requirements

### Python Requirements

<Tip>
  We have support for Python versions **3.9-3.11**
</Tip>

To run the Google Drive ingestion, you will need to install:

```bash theme={null}
pip3 install "openmetadata-ingestion[googledrive]"
```

## Metadata Ingestion

All connectors are defined as JSON Schemas.
[Here](https://github.com/open-metadata/OpenMetadata/blob/main/openmetadata-spec/src/main/resources/json/schema/entity/services/connections/drive/googleDriveConnection.json)
you can find the structure to create a connection to Google Drive.
In order to create and run a Metadata Ingestion workflow, we will follow
the steps to create a YAML configuration able to connect to the source,
process the Entities if needed, and reach the OpenMetadata server.
The workflow is modeled around the following
[JSON Schema](https://github.com/open-metadata/OpenMetadata/blob/main/openmetadata-spec/src/main/resources/json/schema/metadataIngestion/workflow.json)

### 1. Define the YAML Config

This is a sample config for Google Drive:

<CodePreview>
  <ContentPanel>
    <ContentSection id={1} title="Source Configuration" lines="1-3">
      Configure the source type and service name for your Google Drive connector.
    </ContentSection>

    <ContentSection id={2} title="GCP Credentials" lines="7-19">
      **credentials**: GCP service account credentials used to access the Google Drive API. Provide the key file contents directly, or omit this block to fall back to [ADC authentication](https://cloud.google.com/docs/authentication#adc).
    </ContentSection>

    <ContentSection id={3} title="Delegated Email" lines="20">
      **delegatedEmail** (Optional): Email address to impersonate using domain-wide delegation.
    </ContentSection>

    <ContentSection id={4} title="Drive ID" lines="21">
      **driveId** (Optional): Specific shared drive ID to connect to. Leave unset to process all accessible drives.
    </ContentSection>

    <ContentSection id={5} title="Include Team Drives" lines="22">
      **includeTeamDrives**: Include shared/team drives in metadata extraction. Defaults to `true`.
    </ContentSection>

    <ContentSection id={6} title="Include Google Sheets" lines="23">
      **includeGoogleSheets**: Extract metadata for Google Sheets files. Defaults to `false`.
    </ContentSection>

    <ContentSection id={7} title="Filter Patterns" lines="24-33">
      **directoryFilterPattern**, **fileFilterPattern**, **spreadsheetFilterPattern**, **worksheetFilterPattern** (all Optional): Regex to only include/exclude directories, files, spreadsheets, or worksheets that match the pattern.
    </ContentSection>

    <ContentSection id={8} title="Source Config" lines="34-64">
      Configure Drive metadata ingestion options for Google Drive: which entity types to include, deletion handling, owners, and filter patterns.
    </ContentSection>

    <ContentSection id={9} title="Sink Configuration" lines="65-67">
      To send the metadata to OpenMetadata, it needs to be specified as `type: metadata-rest`.
    </ContentSection>

    <ContentSection id={10} title="Workflow Configuration" lines="68-84">
      The main property here is `openMetadataServerConfig`, where you can define the host and security provider of your OpenMetadata installation.

      * **loggerLevel**: Specify the logger level depending on your needs. If you are troubleshooting an ingestion, use `DEBUG` for more detailed traces.
      * **JWT token**: JWT tokens allow clients to authenticate against the OpenMetadata server. See [Enable JWT Tokens](/deployment/security/enable-jwt-tokens) and [JWT Troubleshooting](/deployment/security/jwt-troubleshooting) for more information.
      * **storeServiceConnection**: If set to `true` (default), sensitive information is stored encrypted with the Fernet Key or externally if you have configured a [Secrets Manager](/deployment/secrets-manager). If set to `false`, the service is created, but the service connection information is only used by the Ingestion Framework at runtime and is not sent to the OpenMetadata server.
      * **SSL configuration**: If you have added SSL to the [OpenMetadata server](/deployment/security/enable-ssl), configure the certificates for ingestion. Set `verifySSL` to `ignore`, or set it to `validate` and provide `sslConfig.caCertificate` with a local path to the server certificate. See [SSL Troubleshooting](/deployment/security/enable-ssl/ssl-troubleshooting) for more information.
      * **ingestionPipelineFQN**: Fully qualified name of the ingestion pipeline, used to identify the current ingestion pipeline.
    </ContentSection>
  </ContentPanel>

  <CodePanel fileName="googledrive_config.yaml">
    ```yaml theme={null}
    source:
      type: googledrive
      serviceName: local_googledrive
      serviceConnection:
        config:
          type: GoogleDrive
          credentials:
            gcpConfig:
              type: service_account
              projectId: my-gcp-project
              privateKeyId: "9dd8...db55"
              privateKey: |
                -----BEGIN PRIVATE KEY-----
                <your_private_key_content>
                -----END PRIVATE KEY-----
              clientEmail: gdrive-connector@my-gcp-project.iam.gserviceaccount.com
              clientId: "1234567890"
              authUri: https://accounts.google.com/o/oauth2/auth
              tokenUri: https://oauth2.googleapis.com/token
              authProviderX509CertUrl: https://www.googleapis.com/oauth2/v1/certs
              clientX509CertUrl: https://www.googleapis.com/robot/v1/metadata/x509/gdrive-connector%40my-gcp-project.iam.gserviceaccount.com
          # delegatedEmail: user@yourcompany.com
          # driveId: 0AbCdEfGhIjKlMnOpQ
          includeTeamDrives: true
          includeGoogleSheets: false
          # directoryFilterPattern:
          #   includes:
          #     - /Reports/.*
          #   excludes:
          #     - /Archive/.*
          # fileFilterPattern:
          #   includes:
          #     - .*\.pdf
          #   excludes:
          #     - .*_backup\..*
          # spreadsheetFilterPattern:
          #   includes:
          #     - ^report_.*
          # worksheetFilterPattern:
          #   includes:
          #     - ^Summary.*
    ```

    ```yaml theme={null}
      sourceConfig:
        config:
          type: DriveMetadata
          markDeletedDirectories: true
          markDeletedFiles: true
          markDeletedSpreadsheets: true
          markDeletedWorksheets: true
          includeDirectories: true
          includeFiles: true
          includeSpreadsheets: true
          includeWorksheets: true
          includeTags: true
          includeOwners: false
          overrideMetadata: false
          useFqnForFiltering: false
          # directoryFilterPattern:
          #   includes:
          #     - /Reports/.*
          #   excludes:
          #     - /Archive/.*
          # fileFilterPattern:
          #   includes:
          #     - .*\.pdf
          #     - .*\.docx
          #   excludes:
          #     - .*_backup\..*
          # spreadsheetFilterPattern:
          #   includes:
          #     - ^report_.*
          #   excludes:
          #     - ^draft_.*
          # worksheetFilterPattern:
          #   includes:
          #     - ^Summary.*
          #   excludes:
          #     - ^Sheet\d+$
          threads: 1
    ```

    ```yaml theme={null}
    sink:
      type: metadata-rest
      config: {}
    ```

    ```yaml theme={null}
    workflowConfig:
      loggerLevel: INFO  # DEBUG, INFO, WARNING or ERROR
      openMetadataServerConfig:
        hostPort: "http://localhost:8585/api"
        authProvider: openmetadata
        securityConfig:
          jwtToken: "{bot_jwt_token}"
        ## Store the service Connection information
        storeServiceConnection: true  # false
        ## Secrets Manager Configuration
        # secretsManagerProvider: aws, azure or noop
        # secretsManagerLoader: airflow or env
        ## If SSL, fill the following
        # verifySSL: validate  # or ignore
        # sslConfig:
        #   caCertificate: /local/path/to/certificate
    # ingestionPipelineFQN: <service name>.<ingestion name> ## e.g., "my_redshift.metadata"
    ```
  </CodePanel>
</CodePreview>

### Configuration Examples

#### Service Account with Domain-Wide Delegation

```yaml theme={null}
source:
  type: googledrive
  serviceName: googledrive_prod
  serviceConnection:
    config:
      type: GoogleDrive
      credentials:
        gcpConfig:
          type: service_account
          projectId: my-gcp-project
          privateKeyId: "9dd8...db55"
          privateKey: |
            -----BEGIN PRIVATE KEY-----
            <your_private_key_content>
            -----END PRIVATE KEY-----
          clientEmail: gdrive-connector@my-gcp-project.iam.gserviceaccount.com
          clientId: "1234567890"
          authUri: https://accounts.google.com/o/oauth2/auth
          tokenUri: https://oauth2.googleapis.com/token
          authProviderX509CertUrl: https://www.googleapis.com/oauth2/v1/certs
          clientX509CertUrl: https://www.googleapis.com/robot/v1/metadata/x509/gdrive-connector%40my-gcp-project.iam.gserviceaccount.com
      delegatedEmail: shared-drives@yourcompany.com
      includeTeamDrives: true
```

#### Google Sheets Ingestion with Filtering

```yaml theme={null}
source:
  type: googledrive
  serviceName: googledrive_analytics
  serviceConnection:
    config:
      type: GoogleDrive
      credentials:
        gcpConfig:
          type: service_account
          projectId: my-gcp-project
          privateKeyId: "9dd8...db55"
          privateKey: |
            -----BEGIN PRIVATE KEY-----
            <your_private_key_content>
            -----END PRIVATE KEY-----
          clientEmail: gdrive-connector@my-gcp-project.iam.gserviceaccount.com
          clientId: "1234567890"
          authUri: https://accounts.google.com/o/oauth2/auth
          tokenUri: https://oauth2.googleapis.com/token
          authProviderX509CertUrl: https://www.googleapis.com/oauth2/v1/certs
          clientX509CertUrl: https://www.googleapis.com/robot/v1/metadata/x509/gdrive-connector%40my-gcp-project.iam.gserviceaccount.com
      includeGoogleSheets: true
      spreadsheetFilterPattern:
        includes:
          - ^report_.*
        excludes:
          - ^draft_.*
      worksheetFilterPattern:
        includes:
          - ^Summary.*
        excludes:
          - ^Sheet\d+$
```

### 2. Run with the CLI

First, we will need to save the YAML file. Afterward, and with all requirements installed, we can run:

```bash theme={null}
metadata ingest -c <path-to-yaml>
```

Note that from connector to connector, this recipe will always be the same. By updating the YAML configuration,
you will be able to extract metadata from different sources.

## Related

<Columns cols={2}>
  <Card title="Configure Ingestion Externally" href="/v2.0.x-SNAPSHOT/deployment/ingestion">
    Deploy, configure, and manage the ingestion workflows externally.
  </Card>
</Columns>