<?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 &amp;quot;error_code&amp;quot;:&amp;quot;INVALID_PARAMETER_VALUE&amp;quot;,&amp;quot;message&amp;quot;:&amp;quot;INVALID_PARAMETER_VALUE: Failed to generate access in Machine Learning</title>
    <link>https://community.databricks.com/t5/machine-learning/quot-error-code-quot-quot-invalid-parameter-value-quot-quot/m-p/68005#M3240</link>
    <description>&lt;P&gt;Hello everyone,&lt;/P&gt;&lt;P&gt;I have an Azure Databricks subscription with my company, and I want to use external LLMs in databricks, like claude-3 or gemini. I managed to create a serving endpoint for Anthropic and I am able to use claude 3.&lt;/P&gt;&lt;P&gt;But I want to use a Gemini model through Databricks. I created a Vertex AI account and took a free subscription. I created an API key for my account.&lt;/P&gt;&lt;P&gt;And then I followed the exact steps needed to create an external service endpoint :&lt;/P&gt;&lt;P&gt;- Configure Databricks with the URL of my ressource and my personal token.&lt;/P&gt;&lt;P&gt;- Creation of a scope named "google-scope" and of a key named "dematbl",&amp;nbsp;&lt;EM&gt;dematbl&amp;nbsp;&lt;/EM&gt;being the name of my project.&lt;BR /&gt;I then insert the key value that I got from Vertex AI.&lt;/P&gt;&lt;P&gt;- I go on the creation of a serving endpoint page and I write all the informations (Name of supplier, task, reference of API secret key, name of external model).&lt;/P&gt;&lt;P&gt;I did the exact same steps with Claude-3-sonnet and It works perfectly fine, but It does not work with Gemini. I receive the following error when using the playground :&amp;nbsp;&lt;/P&gt;&lt;PRE&gt;{"error_code":"INVALID_PARAMETER_VALUE","message":"INVALID_PARAMETER_VALUE: Failed to generate access token for Google VertexAI. Please check the private key for the external model gemini-pro."}&lt;/PRE&gt;&lt;P&gt;Thank you for your help.&lt;/P&gt;&lt;P&gt;Léo.&lt;/P&gt;</description>
    <pubDate>Fri, 03 May 2024 07:38:07 GMT</pubDate>
    <dc:creator>Leo69</dc:creator>
    <dc:date>2024-05-03T07:38:07Z</dc:date>
    <item>
      <title>"error_code":"INVALID_PARAMETER_VALUE","message":"INVALID_PARAMETER_VALUE: Failed to generate access</title>
      <link>https://community.databricks.com/t5/machine-learning/quot-error-code-quot-quot-invalid-parameter-value-quot-quot/m-p/68005#M3240</link>
      <description>&lt;P&gt;Hello everyone,&lt;/P&gt;&lt;P&gt;I have an Azure Databricks subscription with my company, and I want to use external LLMs in databricks, like claude-3 or gemini. I managed to create a serving endpoint for Anthropic and I am able to use claude 3.&lt;/P&gt;&lt;P&gt;But I want to use a Gemini model through Databricks. I created a Vertex AI account and took a free subscription. I created an API key for my account.&lt;/P&gt;&lt;P&gt;And then I followed the exact steps needed to create an external service endpoint :&lt;/P&gt;&lt;P&gt;- Configure Databricks with the URL of my ressource and my personal token.&lt;/P&gt;&lt;P&gt;- Creation of a scope named "google-scope" and of a key named "dematbl",&amp;nbsp;&lt;EM&gt;dematbl&amp;nbsp;&lt;/EM&gt;being the name of my project.&lt;BR /&gt;I then insert the key value that I got from Vertex AI.&lt;/P&gt;&lt;P&gt;- I go on the creation of a serving endpoint page and I write all the informations (Name of supplier, task, reference of API secret key, name of external model).&lt;/P&gt;&lt;P&gt;I did the exact same steps with Claude-3-sonnet and It works perfectly fine, but It does not work with Gemini. I receive the following error when using the playground :&amp;nbsp;&lt;/P&gt;&lt;PRE&gt;{"error_code":"INVALID_PARAMETER_VALUE","message":"INVALID_PARAMETER_VALUE: Failed to generate access token for Google VertexAI. Please check the private key for the external model gemini-pro."}&lt;/PRE&gt;&lt;P&gt;Thank you for your help.&lt;/P&gt;&lt;P&gt;Léo.&lt;/P&gt;</description>
      <pubDate>Fri, 03 May 2024 07:38:07 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/quot-error-code-quot-quot-invalid-parameter-value-quot-quot/m-p/68005#M3240</guid>
      <dc:creator>Leo69</dc:creator>
      <dc:date>2024-05-03T07:38:07Z</dc:date>
    </item>
    <item>
      <title>Re: "error_code":"INVALID_PARAMETER_VALUE","message":"INVALID_PAR</title>
      <link>https://community.databricks.com/t5/machine-learning/quot-error-code-quot-quot-invalid-parameter-value-quot-quot/m-p/112184#M3986</link>
      <description>&lt;P&gt;With support from a helpful Databricks employee, we found out that the problem was that the `&lt;SPAN&gt;private_key` / `private_key_plaintext`&amp;nbsp;&lt;/SPAN&gt;field needs to be the &lt;STRONG&gt;entire JSON object&lt;/STRONG&gt; that GCP creates for the service account not just the private key string from it as the documentation lead us to believe&lt;/P&gt;</description>
      <pubDate>Mon, 10 Mar 2025 17:04:33 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/quot-error-code-quot-quot-invalid-parameter-value-quot-quot/m-p/112184#M3986</guid>
      <dc:creator>sam-p</dc:creator>
      <dc:date>2025-03-10T17:04:33Z</dc:date>
    </item>
    <item>
      <title>Re: "error_code":"INVALID_PARAMETER_VALUE","message":"INVALID_PAR</title>
      <link>https://community.databricks.com/t5/machine-learning/quot-error-code-quot-quot-invalid-parameter-value-quot-quot/m-p/116205#M4033</link>
      <description>&lt;P&gt;Thank you&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/152396"&gt;@sam-p&lt;/a&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 22 Apr 2025 14:48:00 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/quot-error-code-quot-quot-invalid-parameter-value-quot-quot/m-p/116205#M4033</guid>
      <dc:creator>reslleygabriel</dc:creator>
      <dc:date>2025-04-22T14:48:00Z</dc:date>
    </item>
  </channel>
</rss>

