https://samarthya.me/tags/langchain/Recent content in Langchain on SamarthyaHugo -- gohugo.ioen© Samarthya 2018-2026. All rights reserved.Tue, 11 Nov 2025 12:00:00 +0000https://samarthya.me/posts/building-a-practical-retrieval-augmented-personal-assistant-rag/Tue, 11 Nov 2025 12:00:00 +0000https://samarthya.me/posts/building-a-practical-retrieval-augmented-personal-assistant-rag/<figure><img class="my-0 rounded-md" loading="lazy" decoding="async" fetchpriority="auto" alt="" width="600" height="600" src="https://samarthya.me/posts/building-a-practical-retrieval-augmented-personal-assistant-rag/rag.png" srcset="https://samarthya.me/posts/building-a-practical-retrieval-augmented-personal-assistant-rag/rag.png 800w, https://samarthya.me/posts/building-a-practical-retrieval-augmented-personal-assistant-rag/rag.png 1280w" sizes="(min-width: 768px) 50vw, 65vw" data-zoom-src="https://samarthya.me/posts/building-a-practical-retrieval-augmented-personal-assistant-rag/rag.png"></figure> <p>The elements of information discussed here are all present in my <a href="https://github.com/samarthya/rag-one.git" target="_blank" rel="noreferrer">github repository</a>.</p> <div class="lead text-neutral-500 dark:text-neutral-400 !mb-9 text-xl"> with <code>Ollama</code>, <code>LangChain</code>, and <code>Chroma</code> </div> <h2 class="relative group">1. Why I Built This <div id="1-why-i-built-this" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#1-why-i-built-this" aria-label="Anchor">#</a> </span> </h2> <p>Large Language Models are powerful, but they hallucinate and forget your private knowledge. We set out to build a small, local Retrieval-Augmented Generation (RAG) assistant that:</p>https://samarthya.me/posts/building-a-minimal-langchain-ollama-demo/Tue, 21 Oct 2025 12:00:00 +0000https://samarthya.me/posts/building-a-minimal-langchain-ollama-demo/<figure><img class="my-0 rounded-md" loading="lazy" decoding="async" fetchpriority="auto" alt="" width="600" height="600" src="https://samarthya.me/posts/building-a-minimal-langchain-ollama-demo/llm-1.png" srcset="https://samarthya.me/posts/building-a-minimal-langchain-ollama-demo/llm-1.png 800w, https://samarthya.me/posts/building-a-minimal-langchain-ollama-demo/llm-1.png 1280w" sizes="(min-width: 768px) 50vw, 65vw" data-zoom-src="https://samarthya.me/posts/building-a-minimal-langchain-ollama-demo/llm-1.png"></figure> <p>This post walks through a tiny, practical example that uses <code>LangChain</code> primitives and a local <code>Ollama</code> server to run a prompt-based summarization. The project is intentionally small so you can learn the core ideas quickly: extracting prompts, initializing an LLM client, composing a chain, and running it locally.</p>