4 posts tagged with "Large Language Model (LLM)"

In the past, in the traditional way, when integrating a new service with your system, you would need to write code to integrate. You would need to check the API document, write code, test and deploy. This takes a lot of time and effort.

With the development of No code / low code systems, you can integrate a new service with your system using a user interface, without having to write too much code. And n8n was born to solve that problem. So what is n8n? Is it a powerful tool that you can take advantage of in your systems? Let's start to find out.

Nowadays, using AI Assistant to support coding is making developers' work easier and more efficient. However, Github products Copilot, Tabnine, Cursor AI ... are all paid products, and the cost of these products is not low, especially for students and those who have just started working. Therefore, in this article, I will share how to use AI Assistant for free to support coding for you.

In the previous article, I guided you how to install Ollama on your personal computer, and also guided you how to install a model on Ollama? Continuing the series of articles related to Large Language Model and Ollama, today I will guide you how to build a simple RAG server, integrated with Ollama.

Nowadays, we can easily access AI chat applications, the most famous of which are ChatGPT by OpenAI, Gemini by Google, Copilot by Microsoft, ... These software are almost free for a normal user, except in cases where you want to use more advanced features, you need to pay to upgrade.

However, if you want to try to build your own personal assistant on your personal computer, and want to freely choose the model, please see the article below, I will guide you in detail.