<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: Deployment-ready sample source-code for Delta Live Table &amp;amp; Autoloader in Data Engineering</title>
    <link>https://community.databricks.com/t5/data-engineering/deployment-ready-sample-source-code-for-delta-live-table-amp/m-p/40126#M27132</link>
    <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/61031"&gt;@Sanjay_AMP&lt;/a&gt;&amp;nbsp;&lt;/P&gt;&lt;DIV class=""&gt;Delta Live Tables and AutoLoader can be used together to incrementally ingest data from cloud object storage.&lt;BR /&gt;• Python code example:&lt;BR /&gt;&amp;nbsp;- Define a table called "customers" that reads data from a CSV file in cloud object storage.&lt;BR /&gt;&amp;nbsp;- Define a table called "sales_orders_raw" that reads data from a JSON file in cloud object storage.&lt;BR /&gt;• SQL code example:&lt;BR /&gt;&amp;nbsp;- Create or refresh a streaming table called "customers" that selects all data from a CSV file in cloud object storage.&lt;BR /&gt;&amp;nbsp;- Create or refresh a streaming table called "sales_orders_raw" that selects all data from a JSON file in cloud object storage.&lt;BR /&gt;• Options can be passed to the&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;cloud_files()&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;method using the&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;map()&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;function.&lt;BR /&gt;• Schema can be specified for formats that don't support schema inference.&lt;BR /&gt;• Additional code examples and documentation can be found at the provided sources.&lt;/DIV&gt;&lt;PRE&gt;@dlt.table
def customers():
  return (
    spark.readStream.format("cloudFiles")
      .option("cloudFiles.format", "csv")
      .load("/databricks-datasets/retail-org/customers/")
  )

@dlt.table
def sales_orders_raw():
  return (
    spark.readStream.format("cloudFiles")
      .option("cloudFiles.format", "json")
      .load("/databricks-datasets/retail-org/sales_orders/")
  )&lt;/PRE&gt;&lt;DIV class=""&gt;&lt;A href="https://docs.databricks.com/en/ingestion/auto-loader/dlt.html" target="_blank" rel="noopener noreferrer"&gt;https://docs.databricks.com/en/ingestion/auto-loader/dlt.html&lt;/A&gt;&lt;/DIV&gt;</description>
    <pubDate>Wed, 16 Aug 2023 22:38:47 GMT</pubDate>
    <dc:creator>Priyanka_Biswas</dc:creator>
    <dc:date>2023-08-16T22:38:47Z</dc:date>
    <item>
      <title>Deployment-ready sample source-code for Delta Live Table &amp; Autoloader</title>
      <link>https://community.databricks.com/t5/data-engineering/deployment-ready-sample-source-code-for-delta-live-table-amp/m-p/39657#M27049</link>
      <description>&lt;P&gt;Hi all,&lt;/P&gt;&lt;P&gt;We are planning to develop an&lt;SPAN&gt;&amp;nbsp;Autoloader based DLT Pipeline that needs to be&lt;/SPAN&gt;&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;&lt;SPAN&gt;Deployable via a CI/CD Pipeline&lt;/SPAN&gt;&lt;/LI&gt;&lt;LI&gt;&lt;SPAN&gt;Observable&lt;/SPAN&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&lt;SPAN&gt;Can somebody&amp;nbsp;please point me to source-code that we can start with a firm foundation instead of falling into a newbie-pattern ?&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Thanks in advance&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Sanjay&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Fri, 11 Aug 2023 13:52:43 GMT</pubDate>
      <guid>https://community.databricks.com/t5/data-engineering/deployment-ready-sample-source-code-for-delta-live-table-amp/m-p/39657#M27049</guid>
      <dc:creator>Sanjay_AMP</dc:creator>
      <dc:date>2023-08-11T13:52:43Z</dc:date>
    </item>
    <item>
      <title>Re: Deployment-ready sample source-code for Delta Live Table &amp; Autoloader</title>
      <link>https://community.databricks.com/t5/data-engineering/deployment-ready-sample-source-code-for-delta-live-table-amp/m-p/40126#M27132</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/61031"&gt;@Sanjay_AMP&lt;/a&gt;&amp;nbsp;&lt;/P&gt;&lt;DIV class=""&gt;Delta Live Tables and AutoLoader can be used together to incrementally ingest data from cloud object storage.&lt;BR /&gt;• Python code example:&lt;BR /&gt;&amp;nbsp;- Define a table called "customers" that reads data from a CSV file in cloud object storage.&lt;BR /&gt;&amp;nbsp;- Define a table called "sales_orders_raw" that reads data from a JSON file in cloud object storage.&lt;BR /&gt;• SQL code example:&lt;BR /&gt;&amp;nbsp;- Create or refresh a streaming table called "customers" that selects all data from a CSV file in cloud object storage.&lt;BR /&gt;&amp;nbsp;- Create or refresh a streaming table called "sales_orders_raw" that selects all data from a JSON file in cloud object storage.&lt;BR /&gt;• Options can be passed to the&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;cloud_files()&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;method using the&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;map()&lt;SPAN&gt;&amp;nbsp;&lt;/SPAN&gt;function.&lt;BR /&gt;• Schema can be specified for formats that don't support schema inference.&lt;BR /&gt;• Additional code examples and documentation can be found at the provided sources.&lt;/DIV&gt;&lt;PRE&gt;@dlt.table
def customers():
  return (
    spark.readStream.format("cloudFiles")
      .option("cloudFiles.format", "csv")
      .load("/databricks-datasets/retail-org/customers/")
  )

@dlt.table
def sales_orders_raw():
  return (
    spark.readStream.format("cloudFiles")
      .option("cloudFiles.format", "json")
      .load("/databricks-datasets/retail-org/sales_orders/")
  )&lt;/PRE&gt;&lt;DIV class=""&gt;&lt;A href="https://docs.databricks.com/en/ingestion/auto-loader/dlt.html" target="_blank" rel="noopener noreferrer"&gt;https://docs.databricks.com/en/ingestion/auto-loader/dlt.html&lt;/A&gt;&lt;/DIV&gt;</description>
      <pubDate>Wed, 16 Aug 2023 22:38:47 GMT</pubDate>
      <guid>https://community.databricks.com/t5/data-engineering/deployment-ready-sample-source-code-for-delta-live-table-amp/m-p/40126#M27132</guid>
      <dc:creator>Priyanka_Biswas</dc:creator>
      <dc:date>2023-08-16T22:38:47Z</dc:date>
    </item>
  </channel>
</rss>

