<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>langchain on Rise-</title><link>https://madil.in/tag/langchain/</link><description>Recent content in langchain on Rise-</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 18 Apr 2025 09:00:53 +0000</lastBuildDate><atom:link href="https://madil.in/tag/langchain/index.xml" rel="self" type="application/rss+xml"/><item><title>AI-Powered Cloud Configuration Review</title><link>https://madil.in/ai-powered-cloud-configuration-review/</link><pubDate>Fri, 18 Apr 2025 09:00:53 +0000</pubDate><guid>https://madil.in/ai-powered-cloud-configuration-review/</guid><description>&lt;p&gt;In today&amp;rsquo;s fast-paced cloud landscape, keeping cloud environments secure is a challenge. Misconfigurations have become a leading cause of data breaches, and manually researching and reviewing every configuration is time-consuming and prone to error. But what if we could leverage the power of Generative AI to enhance this process?&lt;/p&gt;&#10;&lt;p&gt;In this blog post, we&amp;rsquo;ll go through a capstone project that I have built to enhance my cloud configuration review process. This was possible after taking &lt;a href="https://blog.google/technology/developers/google-kaggle-genai-intensive/"&gt;Google and Kaggle’s free GenAI Intensive course&lt;/a&gt;. This course gave me a strong understanding of generative AI, from the basics of large language models (LLMs) to using gen AI with tools in production. The course was carefully designed and explored a broad variety of topics:&lt;/p&gt;</description></item><item><title>Hot Take - Learn Async Programming before LangChain and LangGraph</title><link>https://madil.in/importance-of-async-programming/</link><pubDate>Tue, 04 Feb 2025 17:00:17 +0000</pubDate><guid>https://madil.in/importance-of-async-programming/</guid><description>&lt;p&gt;I heard you are building production-grade AI applications with LangChain and LangGraph. If yes, I highly recommend learning Async Programming.&lt;/p&gt;&#10;&lt;p&gt;AI applications in general are pretty computationally intensive. Especially those multi-agent and multi-tool workflows that work in real-time to fetch and process data while talking to LLMs. Instead of waiting for each operation to complete sequentially, incorporating async programming can allocate resources like CPU and GPU time more efficiently between multiple tasks.&lt;/p&gt;</description></item><item><title>Tagging and Summarizing Articles with OpenAI and LangChain</title><link>https://madil.in/tagging-and-summarizing-articles-with-openai-and-langchain/</link><pubDate>Fri, 17 Jan 2025 14:45:20 +0000</pubDate><guid>https://madil.in/tagging-and-summarizing-articles-with-openai-and-langchain/</guid><description>&lt;p&gt;In this post, we build a simple AI-enabled application for tagging and summarizing articles by leveraging OpenAI and LangChain.&lt;/p&gt;&#10;&lt;blockquote&gt;&#10;&lt;p&gt;📌 TLDR; we will try to mimic some functionality of &lt;a href="https://m.inshorts.com/"&gt;Inshorts&lt;/a&gt;.&lt;/p&gt;&#10;&lt;/blockquote&gt;&#10;&lt;p&gt;Under the hood, our application will use &lt;a href="https://platform.openai.com/docs/guides/function-calling"&gt;OpenAI function calling&lt;/a&gt; to interact with a Large Language Model and get a structured output with a summary of the article, its language, and associated tags.&lt;/p&gt;&#10;&lt;p&gt;Firstly, we import our OpenAPI Key in the environment variable and add the necessary imports.&lt;/p&gt;</description></item></channel></rss>