<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Openai on Selvam Subbiah</title><link>https://selvamsubbiah.com/tags/openai/</link><description>Recent content in Openai on Selvam Subbiah</description><generator>Hugo -- 0.154.3</generator><language>en-us</language><lastBuildDate>Fri, 16 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://selvamsubbiah.com/tags/openai/index.xml" rel="self" type="application/rss+xml"/><item><title>Google ADK + LiteLLM: Build Model-Agnostic Agents (Gemini, OpenAI, Claude)</title><link>https://selvamsubbiah.com/google-adk-litellm-model-agnostic-agents/</link><pubDate>Fri, 16 Jan 2026 00:00:00 +0000</pubDate><guid>https://selvamsubbiah.com/google-adk-litellm-model-agnostic-agents/</guid><description>&lt;p&gt;&lt;em&gt;Switch between OpenAI, Claude, and Gemini with one line of code&lt;/em&gt;&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;&lt;strong&gt;📚 Series Navigation:&lt;/strong&gt; This is &lt;strong&gt;Post 2&lt;/strong&gt; of the Google ADK Tutorial Series.&lt;br&gt;
← Previous: &lt;a href="https://selvamsubbiah.com/introduction-to-google-adk/"&gt;Introduction to Google ADK&lt;/a&gt;
&lt;/p&gt;
&lt;/blockquote&gt;
&lt;hr&gt;
&lt;h2 id="what-youll-learn"&gt;What You&amp;rsquo;ll Learn&lt;/h2&gt;
&lt;p&gt;By the end of this post, you&amp;rsquo;ll:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Understand how LiteLLM works with ADK&lt;/li&gt;
&lt;li&gt;Configure multiple LLM providers&lt;/li&gt;
&lt;li&gt;Switch between models without changing code&lt;/li&gt;
&lt;li&gt;Implement fallback strategies for reliability&lt;/li&gt;
&lt;li&gt;Optimize costs by choosing the right model for each task&lt;/li&gt;
&lt;/ul&gt;
&lt;blockquote&gt;
&lt;p&gt;&lt;strong&gt;Code on GitHub&lt;/strong&gt;: The complete working example from this post is available at &lt;a href="https://github.com/selvam85/google-adk-samples/tree/main/model_agnostic_agent" target="_blank" rel="noopener noreferrer"&gt;google-adk-samples/model_agnostic_agent&lt;/a&gt;
&lt;/p&gt;</description></item><item><title>Auto-generate MongoDB Queries with OpenAI Assistants API</title><link>https://selvamsubbiah.com/auto-generate-mongodb-queries-with-openai-assistants-api/</link><pubDate>Wed, 31 Jan 2024 00:00:00 +0000</pubDate><guid>https://selvamsubbiah.com/auto-generate-mongodb-queries-with-openai-assistants-api/</guid><description>&lt;p&gt;This is a continuation to the &lt;a href="https://selvamsubbiah.com/mastering-mongodb-queries-with-openai/"&gt;previous article&lt;/a&gt;
on generating MongoDB Queries using &lt;a href="https://platform.openai.com/docs/guides/text-generation/chat-completions-api" target="_blank" rel="noopener noreferrer"&gt;OpenAI Chat Completion API&lt;/a&gt;
. In this article, we will look at how to construct MongoDB Queries using &lt;a href="https://platform.openai.com/docs/assistants/overview" target="_blank" rel="noopener noreferrer"&gt;OpenAI Assistants API&lt;/a&gt;
given an input and an expected output.&lt;/p&gt;
&lt;p&gt;In this article, we will cover the following:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;
&lt;p&gt;Create an assistant using Assistants API and use it to generate MongoDB queries.&lt;/p&gt;
&lt;/li&gt;
&lt;li&gt;
&lt;p&gt;Use custom function tool to format the output in JSON format.&lt;/p&gt;</description></item><item><title>Mastering MongoDB Queries with OpenAI: A Guide to Generating Queries for Desired Outputs</title><link>https://selvamsubbiah.com/mastering-mongodb-queries-with-openai/</link><pubDate>Mon, 08 Jan 2024 00:00:00 +0000</pubDate><guid>https://selvamsubbiah.com/mastering-mongodb-queries-with-openai/</guid><description>&lt;p&gt;I’m a big fan of &lt;a href="https://mongoplayground.net/" target="_blank" rel="noopener noreferrer"&gt;mongoplayground.net&lt;/a&gt;
as it is one of the most useful and widely used tools for swiftly testing various MongoDB queries while working on a problem. Although this tool is really handy and convenient to use, I have always wondered if there is a way to automatically generate the query for a given input and an expected output, rather than having to manually construct these queries.&lt;/p&gt;
&lt;p&gt;Thanks to Generative AI tools, this is now possible!&lt;/p&gt;</description></item></channel></rss>