The latest articles on DEV Community by swathy s kumar (@ai_literacy_lab). https://dev.to/ai_literacy_lab https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4230860%2F5f4ce157-096c-491c-8806-3423403afb85.png https://dev.to/ai_literacy_lab en swathy s kumar Fri, 06 Nov 2026 17:13:56 +0000 https://dev.to/ai_literacy_lab/i-built-a-fully-offline-rag-system-on-my-laptop-with-ollama-zero-api-fees-1h74 https://dev.to/ai_literacy_lab/i-built-a-fully-offline-rag-system-on-my-laptop-with-ollama-zero-api-fees-1h74 <p>Just published a short practical video where I run RAG completely offline on my own laptop using Ollama.</p> <p>No cloud, no API keys, no data leaving the machine.</p> <p>In the video I show:</p> <p>Setting up local RAG</p> <p>Keeping everything private</p> <p>Avoiding the usual hallucination issues that happen with closed-book models</p> <p>Video: <a href="https://youtu.be/BnTr9Vf255Y?si=5Nr6PvuYJdYw9uAv" rel="noopener noreferrer">https://youtu.be/BnTr9Vf255Y?si=5Nr6PvuYJdYw9uAv</a></p> <p>GitHub:<a href="https://github.com/AI-Literacy-Lab/localrag" rel="noopener noreferrer">https://github.com/AI-Literacy-Lab/localrag</a></p> <p>Would love feedback from people who are also running local RAG setups. What models and embedding setups are you finding most reliable right now?[Build Local rag](<a href="https://youtu.be/BnTr9Vf255Y" rel="noopener noreferrer">https://youtu.be/BnTr9Vf255Y</a>)</p> ai rag langchain