> ## 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 Delta Lake Connector Externally

> Configure Delta Lake ingestion using YAML to extract structured metadata, table properties, and data lineage.

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/delta-lake.webp" name="Delta Lake" stage="PROD" availableFeatures={["Metadata", "dbt"]} unavailableFeatures={["Query Usage", "Data Profiler", "Data Quality", "Lineage", "Column-level Lineage", "Owners", "Tags", "Stored Procedures", "Sample Data", "Auto-Classification"]} />

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

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

## 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="/v1.12.x/deployment/ingestion">
    Get more information about running the Ingestion Framework Externally
  </Card>
</Columns>

## Requirements

Delta Lake requires to run with Python 3.9 or 3.10. We do not yet support the Delta connector
for Python 3.11

### Python Requirements

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

To run the Delta Lake ingestion, you will need to install:

* If extracting from a metastore

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

* If extracting directly from the storage

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

## 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/database/deltaLakeConnection.json)
you can find the structure to create a connection to Delta Lake.
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

#### Source Configuration - From Metastore

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

    <ContentSection id={2} title="Metastore Configuration" lines="11">
      **Metastore Host Port**: Enter the Host & Port of Hive Metastore Service to configure the Spark Session. Either of `metastoreHostPort`, `metastoreDb` or `metastoreFilePath` is required.

      **Metastore File Path**: Enter the file path to local Metastore in case Spark cluster is running locally. Either of `metastoreHostPort`, `metastoreDb` or `metastoreFilePath` is required.

      **Metastore DB**: The JDBC connection to the underlying Hive metastore DB. Either of `metastoreHostPort`, `metastoreDb` or `metastoreFilePath` is required.

      When connecting to an External Metastore passing the parameter `Metastore Host Port`, we will be preparing a Spark Session with the configuration `.config("hive.metastore.uris", "thrift://{connection.metastoreHostPort}")`.

      For local file path metastore, we will set `.config("spark.driver.extraJavaOptions", "-Dderby.system.home={connection.metastoreFilePath}")`.

      You can also connect to the metastore by directly pointing to the Hive Metastore db, e.g., `jdbc:mysql://localhost:3306/demo_hive`. Here, we will need to inform all the common database settings (url, username, password), and the driver class name for JDBC metastore.
    </ContentSection>

    <ContentSection id={3} title="App Name" lines="12">
      **appName (Optional)**: Enter the app name of spark session.
    </ContentSection>

    <ContentSection id={4} title="Connection Options" lines="13">
      **Connection Options (Optional)**: Enter the details for any additional connection options that can be sent to database during the connection. These details must be added as Key-Value pairs.
    </ContentSection>

    <ContentSection id={5} title="Connection Arguments" lines="14">
      **Connection Arguments (Optional)**: Key-Value pairs that will be used to pass extra `config` elements to the Spark Session builder.

      We are internally running with `pyspark` 3.X and `delta-lake` 2.0.0. This means that we need to consider Spark configuration options for 3.X.

      * In case you are using Single-Sign-On (SSO) for authentication, add the `authenticator` details in the Connection Arguments as a Key-Value pair as follows: `"authenticator" : "sso_login_url"`
    </ContentSection>

    <ContentSection id={6} title="Source Config" lines="25-68">
      #### Source Configuration - Source Config

      The `sourceConfig` is defined [here](https://github.com/open-metadata/OpenMetadata/blob/main/openmetadata-spec/src/main/resources/json/schema/metadataIngestion/databaseServiceMetadataPipeline.json):

      <div>
        **markDeletedTables**: To flag tables as soft-deleted if they are not present anymore in the source system.
      </div>

      <div>
        **markDeletedStoredProcedures**: Optional configuration to soft delete stored procedures in OpenMetadata if the source stored procedures are deleted. Also, if the stored procedures is deleted, all the associated entities like lineage, etc., with that stored procedures will be deleted.

        **markDeletedSchemas**: Optional configuration to soft delete schemas stored in OpenMetadata if the source schema is deleted. Setting this flag to true will only keep filtered schema and delete any other schemas that do not match schemaFilterPattern or do not exist at source.

        **markDeletedDatabases**: Additional optional configuration for soft deletion, providing granular option to select which particular entities should be deleted.

        **includeTables**: true or false, to ingest table data. Default is true.
      </div>

      <div>
        **includeViews**: true or false, to ingest views definitions.
      </div>

      <div>
        **includeTags**: Optional configuration to toggle the tags ingestion.
      </div>

      <div>
        **includeOwners**: Set the 'Include Owners' toggle to control whether to include owners to the ingested entity if the owner email matches with a user stored in the OM server as part of metadata ingestion. If the ingested entity already exists and has an owner, the owner will not be overwritten.
      </div>

      <div>
        **includeStoredProcedures**: Optional configuration to toggle the Stored Procedures ingestion.
      </div>

      <div>
        **includeDDL**: Optional configuration to toggle the DDL Statements ingestion.
      </div>

      <div>
        **overrideMetadata** *(boolean)*: Set the 'Override Metadata' toggle to control whether to override the existing metadata in the OpenMetadata server with the metadata fetched from the source. If the toggle is set to true, the metadata fetched from the source will override the existing metadata in the OpenMetadata server. If the toggle is set to false, the metadata fetched from the source will not override the existing metadata in the OpenMetadata server. This is applicable for fields like description, tags, owner and displayName.
      </div>

      <div>
        **queryLogDuration**: Configuration to tune how far we want to look back in query logs to process Stored Procedures results.
      </div>

      <div>
        **queryParsingTimeoutLimit**: Configuration to set the timeout for parsing the query in seconds.
      </div>

      <div>
        **useFqnForFiltering**: Regex will be applied on fully qualified name (e.g service\_name.db\_name.schema\_name.table\_name) instead of raw name (e.g. table\_name).
      </div>

      <div>
        **databaseFilterPattern**, **schemaFilterPattern**: Note that the filter supports regex as include or exclude. You can find examples [here](/connectors/ingestion/workflows/metadata/filter-patterns/database)
      </div>

      <div>
        **tableFilterPattern**: Note that the filter supports regex as include or exclude. You can find examples [here](/connectors/ingestion/workflows/metadata/filter-patterns/table)
      </div>

      <div>
        **threads (beta)**: The number of threads to use when extracting the metadata using multithreading.
      </div>

      <div>
        **databaseMetadataConfigType** *(string)*: Database Source Config Metadata Pipeline type.
      </div>

      <div>
        **incremental (beta)**: Incremental Extraction configuration. Currently implemented for:

        * [BigQuery](/connectors/ingestion/workflows/metadata/incremental-extraction/bigquery)
        * [Redshift](/connectors/ingestion/workflows/metadata/incremental-extraction/redshift)
        * [Snowflake](/connectors/ingestion/workflows/metadata/incremental-extraction/snowflake)
      </div>
    </ContentSection>

    <ContentSection id={7} title="Sink Configuration" lines="69-71">
      To send the metadata to OpenMetadata, it needs to be specified as `type: metadata-rest`.
    </ContentSection>

    <ContentSection id={8} title="Workflow Configuration" lines="72-88">
      <div>
        The main property here is the `openMetadataServerConfig`, where you can define the host and security provider of your OpenMetadata installation.
      </div>

      <div>
        **Logger Level**

        You can specify the `loggerLevel` depending on your needs. If you are trying to troubleshoot an ingestion, running with `DEBUG` will give you far more traces for identifying issues.
      </div>

      <div>
        **JWT Token**

        JWT tokens will allow your clients to authenticate against the OpenMetadata server. To enable JWT Tokens, you will get more details [here](/deployment/security/enable-jwt-tokens).

        You can refer to the JWT Troubleshooting section [link](/deployment/security/jwt-troubleshooting) for any issues in your JWT configuration.
      </div>

      <div>
        **Store Service Connection**

        If set to `true` (default), we will store the sensitive information either encrypted via the Fernet Key in the database or externally, if you have configured any [Secrets Manager](/deployment/secrets-manager).

        If set to `false`, the service will be created, but the service connection information will only be used by the Ingestion Framework at runtime, and won't be sent to the OpenMetadata server.
      </div>

      <div>
        **SSL Configuration**

        If you have added SSL to the [OpenMetadata server](/deployment/security/enable-ssl), then you will need to handle the certificates when running the ingestion too. You can either set `verifySSL` to `ignore`, or have it as `validate`, which will require you to set the `sslConfig.caCertificate` with a local path where your ingestion runs that points to the server certificate file.

        Find more information on how to troubleshoot SSL issues [here](/deployment/security/enable-ssl/ssl-troubleshooting).
      </div>

      <div>
        **ingestionPipelineFQN**

        Fully qualified name of ingestion pipeline, used to identify the current ingestion pipeline.
      </div>
    </ContentSection>
  </ContentPanel>

  <CodePanel fileName="deltalake_metastore_config.yaml">
    ```yaml theme={null}
    source:
      type: deltalake
      serviceName: "<service name>"
      serviceConnection:
        config:
          type: DeltaLake
          configSource:
            connection:
              # Pick only one of these
              ## 1. Hive Service Thrift Connection
              metastoreHostPort: "<metastore host port>"
              ## 2. Hive Metastore db connection
              # metastoreDb: jdbc:mysql://localhost:3306/demo_hive
              # username: username
              # password: password
              # driverName: org.mariadb.jdbc.Driver
              # jdbcDriverClassPath: /some/path/
              ## 3. Local file for Testing
              # metastoreFilePath: "<path_to_metastore>/metastore_db"
              appName: MyApp
              # connectionOptions:
              #   key: value
              # connectionArguments:
              #   key: value
    ```

    ```yaml theme={null}
      sourceConfig:
        config:
          type: DatabaseMetadata
          markDeletedTables: true
          markDeletedStoredProcedures: true
          markDeletedSchemas: true
          markDeletedDatabases: true
          includeTables: true
          includeViews: true
          # includeTags: true
          # includeOwners: false
          # includeStoredProcedures: true
          # includeDDL: true
          # overrideMetadata: false
          # queryLogDuration: 1
          # queryParsingTimeoutLimit: 300
          # useFqnForFiltering: false
          # threads: 1
          # databaseMetadataConfigType: ()
          # incremental:
          #   enabled: true
          #   lookbackDays: 7
          #   safetyMarginDays: 1
          # databaseFilterPattern:
          #   includes:
          #     - database1
          #     - database2
          #   excludes:
          #     - database3
          #     - database4
          # schemaFilterPattern:
          #   includes:
          #     - schema1
          #     - schema2
          #   excludes:
          #     - schema3
          #     - schema4
          # tableFilterPattern:
          #   includes:
          #     - users
          #     - type_test
          #   excludes:
          #     - table3
          #     - table4
    ```

    ```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>

#### Source Configuration - From Storage - S3

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

    <ContentSection id={2} title="AWS Configuration" lines="9-12">
      **awsAccessKeyId**: Enter your secure access key ID for your DynamoDB connection. The specified key ID should be authorized to read all databases you want to include in the metadata ingestion workflow.

      **awsSecretAccessKey**: Enter the Secret Access Key (the passcode key pair to the key ID from above).

      **awsRegion**: Specify the region in which your DynamoDB is located. This setting is required even if you have configured a local AWS profile.
    </ContentSection>

    <ContentSection id={3} title="Bucket Configuration" lines="13-14">
      **bucketName**: The S3 bucket name where your Delta Lake tables are stored.

      **prefix**: Optional prefix path within the bucket.
    </ContentSection>

    <ContentSection id={4} title="Source Config" lines="15-58">
      #### Source Configuration - Source Config

      The `sourceConfig` is defined [here](https://github.com/open-metadata/OpenMetadata/blob/main/openmetadata-spec/src/main/resources/json/schema/metadataIngestion/databaseServiceMetadataPipeline.json):

      <div>
        **markDeletedTables**: To flag tables as soft-deleted if they are not present anymore in the source system.
      </div>

      <div>
        **markDeletedStoredProcedures**: Optional configuration to soft delete stored procedures in OpenMetadata if the source stored procedures are deleted. Also, if the stored procedures is deleted, all the associated entities like lineage, etc., with that stored procedures will be deleted.

        **markDeletedSchemas**: Optional configuration to soft delete schemas stored in OpenMetadata if the source schema is deleted. Setting this flag to true will only keep filtered schema and delete any other schemas that do not match schemaFilterPattern or do not exist at source.

        **markDeletedDatabases**: Additional optional configuration for soft deletion, providing granular option to select which particular entities should be deleted.

        **includeTables**: true or false, to ingest table data. Default is true.
      </div>

      <div>
        **includeViews**: true or false, to ingest views definitions.
      </div>

      <div>
        **includeTags**: Optional configuration to toggle the tags ingestion.
      </div>

      <div>
        **includeOwners**: Set the 'Include Owners' toggle to control whether to include owners to the ingested entity if the owner email matches with a user stored in the OM server as part of metadata ingestion. If the ingested entity already exists and has an owner, the owner will not be overwritten.
      </div>

      <div>
        **includeStoredProcedures**: Optional configuration to toggle the Stored Procedures ingestion.
      </div>

      <div>
        **includeDDL**: Optional configuration to toggle the DDL Statements ingestion.
      </div>

      <div>
        **overrideMetadata** *(boolean)*: Set the 'Override Metadata' toggle to control whether to override the existing metadata in the OpenMetadata server with the metadata fetched from the source. If the toggle is set to true, the metadata fetched from the source will override the existing metadata in the OpenMetadata server. If the toggle is set to false, the metadata fetched from the source will not override the existing metadata in the OpenMetadata server. This is applicable for fields like description, tags, owner and displayName.
      </div>

      <div>
        **queryLogDuration**: Configuration to tune how far we want to look back in query logs to process Stored Procedures results.
      </div>

      <div>
        **queryParsingTimeoutLimit**: Configuration to set the timeout for parsing the query in seconds.
      </div>

      <div>
        **useFqnForFiltering**: Regex will be applied on fully qualified name (e.g service\_name.db\_name.schema\_name.table\_name) instead of raw name (e.g. table\_name).
      </div>

      <div>
        **databaseFilterPattern**, **schemaFilterPattern**: Note that the filter supports regex as include or exclude. You can find examples [here](/connectors/ingestion/workflows/metadata/filter-patterns/database)
      </div>

      <div>
        **tableFilterPattern**: Note that the filter supports regex as include or exclude. You can find examples [here](/connectors/ingestion/workflows/metadata/filter-patterns/table)
      </div>

      <div>
        **threads (beta)**: The number of threads to use when extracting the metadata using multithreading.
      </div>

      <div>
        **databaseMetadataConfigType** *(string)*: Database Source Config Metadata Pipeline type.
      </div>

      <div>
        **incremental (beta)**: Incremental Extraction configuration. Currently implemented for:

        * [BigQuery](/connectors/ingestion/workflows/metadata/incremental-extraction/bigquery)
        * [Redshift](/connectors/ingestion/workflows/metadata/incremental-extraction/redshift)
        * [Snowflake](/connectors/ingestion/workflows/metadata/incremental-extraction/snowflake)
      </div>
    </ContentSection>

    <ContentSection id={5} title="Sink Configuration" lines="59-61">
      To send the metadata to OpenMetadata, it needs to be specified as `type: metadata-rest`.
    </ContentSection>

    <ContentSection id={6} title="Workflow Configuration" lines="62-78">
      <div>
        The main property here is the `openMetadataServerConfig`, where you can define the host and security provider of your OpenMetadata installation.
      </div>

      <div>
        **Logger Level**

        You can specify the `loggerLevel` depending on your needs. If you are trying to troubleshoot an ingestion, running with `DEBUG` will give you far more traces for identifying issues.
      </div>

      <div>
        **JWT Token**

        JWT tokens will allow your clients to authenticate against the OpenMetadata server. To enable JWT Tokens, you will get more details [here](/deployment/security/enable-jwt-tokens).

        You can refer to the JWT Troubleshooting section [link](/deployment/security/jwt-troubleshooting) for any issues in your JWT configuration.
      </div>

      <div>
        **Store Service Connection**

        If set to `true` (default), we will store the sensitive information either encrypted via the Fernet Key in the database or externally, if you have configured any [Secrets Manager](/deployment/secrets-manager).

        If set to `false`, the service will be created, but the service connection information will only be used by the Ingestion Framework at runtime, and won't be sent to the OpenMetadata server.
      </div>

      <div>
        **SSL Configuration**

        If you have added SSL to the [OpenMetadata server](/deployment/security/enable-ssl), then you will need to handle the certificates when running the ingestion too. You can either set `verifySSL` to `ignore`, or have it as `validate`, which will require you to set the `sslConfig.caCertificate` with a local path where your ingestion runs that points to the server certificate file.

        Find more information on how to troubleshoot SSL issues [here](/deployment/security/enable-ssl/ssl-troubleshooting).
      </div>

      <div>
        **ingestionPipelineFQN**

        Fully qualified name of ingestion pipeline, used to identify the current ingestion pipeline.
      </div>
    </ContentSection>
  </ContentPanel>

  <CodePanel fileName="deltalake_s3_config.yaml">
    ```yaml theme={null}
    source:
      type: deltalake
      serviceName: <service_name>
      serviceConnection:
        config:
          type: DeltaLake
          configSource:
            connection:
              securityConfig:
                awsAccessKeyId: aws access key id  # REQUIRED
                awsSecretAccessKey: aws secret access key  # REQUIRED
                awsRegion: aws region  # REQUIRED
            bucketName: bucket name  # REQUIRED
            prefix: prefix
    ```

    ```yaml theme={null}
      sourceConfig:
        config:
          type: DatabaseMetadata
          markDeletedTables: true
          markDeletedStoredProcedures: true
          markDeletedSchemas: true
          markDeletedDatabases: true
          includeTables: true
          includeViews: true
          # includeTags: true
          # includeOwners: false
          # includeStoredProcedures: true
          # includeDDL: true
          # overrideMetadata: false
          # queryLogDuration: 1
          # queryParsingTimeoutLimit: 300
          # useFqnForFiltering: false
          # threads: 1
          # databaseMetadataConfigType: ()
          # incremental:
          #   enabled: true
          #   lookbackDays: 7
          #   safetyMarginDays: 1
          # databaseFilterPattern:
          #   includes:
          #     - database1
          #     - database2
          #   excludes:
          #     - database3
          #     - database4
          # schemaFilterPattern:
          #   includes:
          #     - schema1
          #     - schema2
          #   excludes:
          #     - schema3
          #     - schema4
          # tableFilterPattern:
          #   includes:
          #     - users
          #     - type_test
          #   excludes:
          #     - table3
          #     - table4
    ```

    ```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>

### 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.

## dbt Integration

<Columns cols={2}>
  <Card title="dbt Integration" href="/v1.12.x/connectors/database/dbt">
    Learn more about how to ingest dbt models
  </Card>
</Columns>