<?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: Questions about the Knowledge Assistant during agentBrick in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/questions-about-the-knowledge-assistant-during-agentbrick/m-p/121988#M961</link>
    <description>&lt;P&gt;Hi &lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/169342"&gt;@Remy&lt;/a&gt;,&amp;nbsp;&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;Yes, you can define input and output schemas in Databricks, typically using formats like Python dictionaries, especially when working with Vector Search indexes.&lt;/LI&gt;&lt;LI&gt;Free Edition allows only one Vector Search endpoint per workspace, so creating additional endpoints (as for Knowledge Assistants) isn’t supported.&lt;/LI&gt;&lt;LI&gt;The DIRECT_ACCESS index type isn’t available in the Free Edition.&lt;/LI&gt;&lt;/UL&gt;</description>
    <pubDate>Tue, 17 Jun 2025 13:19:42 GMT</pubDate>
    <dc:creator>Renu_</dc:creator>
    <dc:date>2025-06-17T13:19:42Z</dc:date>
    <item>
      <title>Questions about the Knowledge Assistant during agentBrick</title>
      <link>https://community.databricks.com/t5/generative-ai/questions-about-the-knowledge-assistant-during-agentbrick/m-p/121690#M953</link>
      <description>&lt;P&gt;hello.&lt;BR /&gt;I'm testing agentBricks right now. As I'm testing, I have a few questions that I'd like to ask.&lt;/P&gt;&lt;P&gt;1) Is it possible to input the schema in a format with input and output?&lt;/P&gt;&lt;P&gt;2) In the free trial, when I create a vector search index and utilize it as a knowledge source, I get the following error.&lt;/P&gt;&lt;P&gt;Maximum number of vector search endpoints per workspace exceeded quota of 1&lt;/P&gt;&lt;P&gt;Is it impossible to create a vector search index in the free trial and utilize it as a Knowledge source to build the Knowledge Assistant?&lt;/P&gt;&lt;P&gt;3) Why do I get the following error? I built Knowledge Assistant by setting UC Files as the Type of Knowledge source.&lt;/P&gt;&lt;P&gt;Vector index type DIRECT_ACCESS is not supported for this workspace.&lt;/P&gt;</description>
      <pubDate>Fri, 13 Jun 2025 06:28:42 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/questions-about-the-knowledge-assistant-during-agentbrick/m-p/121690#M953</guid>
      <dc:creator>Remy</dc:creator>
      <dc:date>2025-06-13T06:28:42Z</dc:date>
    </item>
    <item>
      <title>Re: Questions about the Knowledge Assistant during agentBrick</title>
      <link>https://community.databricks.com/t5/generative-ai/questions-about-the-knowledge-assistant-during-agentbrick/m-p/121988#M961</link>
      <description>&lt;P&gt;Hi &lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/169342"&gt;@Remy&lt;/a&gt;,&amp;nbsp;&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;Yes, you can define input and output schemas in Databricks, typically using formats like Python dictionaries, especially when working with Vector Search indexes.&lt;/LI&gt;&lt;LI&gt;Free Edition allows only one Vector Search endpoint per workspace, so creating additional endpoints (as for Knowledge Assistants) isn’t supported.&lt;/LI&gt;&lt;LI&gt;The DIRECT_ACCESS index type isn’t available in the Free Edition.&lt;/LI&gt;&lt;/UL&gt;</description>
      <pubDate>Tue, 17 Jun 2025 13:19:42 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/questions-about-the-knowledge-assistant-during-agentbrick/m-p/121988#M961</guid>
      <dc:creator>Renu_</dc:creator>
      <dc:date>2025-06-17T13:19:42Z</dc:date>
    </item>
    <item>
      <title>Re: Questions about the Knowledge Assistant during agentBrick</title>
      <link>https://community.databricks.com/t5/generative-ai/questions-about-the-knowledge-assistant-during-agentbrick/m-p/122046#M964</link>
      <description>&lt;P&gt;So how do you avoid getting the error below?&lt;BR /&gt;Please tell me how to avoid getting the error when Knowledge source with UC Files Type.&lt;/P&gt;&lt;P&gt;Vector index type DIRECT_ACCESS is not supported for this workspace.&lt;/P&gt;</description>
      <pubDate>Wed, 18 Jun 2025 00:04:13 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/questions-about-the-knowledge-assistant-during-agentbrick/m-p/122046#M964</guid>
      <dc:creator>Remy</dc:creator>
      <dc:date>2025-06-18T00:04:13Z</dc:date>
    </item>
  </channel>
</rss>

