RAGGINThis project focuses on the development of a Retrieval-Augmented Generation (RAG) system, which enhances the capabilities of Large Language Models (LLMs) by incorporating information retrieval from external data sources. Installation Launch VS Code Quick Open ( Ctrl+P), paste the following command, and press enter.Copied to clipboard |
🚀 RAGGIN IntroductionRAGGIN (Retrieval-Augmented Generation for Guided Intelligence in Next.js) is a powerful Visual Studio Code extension designed to assist developers working with the Next.js framework. It provides intelligent, real-time support for tasks such as:
RAGGIN delivers answers directly inside the editor, so developers can stay focused in their coding environment without needing to switch between browser tabs or external documentation tools. One of RAGGIN's key features is the ability to ask questions based on a specific version of the Next.js documentation. This ensures that answers are accurate and relevant to the version you're working with, helping avoid deprecated or outdated information. RAGGIN operates 100% locally, powered by Docker and Ollama, eliminating the need for an internet connection during use. However, some resources—such as versioned Next.js documentation and local LLMs—must be downloaded beforehand. By ensuring that all processing happens on your machine, RAGGIN maintains data privacy and keeps your development environment secure from external data exposure. It's a smart, privacy-focused solution for modern web developers. 🔧 RAGGIN Installation GuideTo make RAGGIN runable, make sure these components are installed and configured properly: 🧠 Ollama Installation GuideRAGGIN relies on Ollama to run a local Large Language Model (LLM) for answering Next.js-related questions. To ensure RAGGIN works properly, both Ollama and at least one LLM model must be installed on your system. ✅ Step 1: Install OllamaVisit https://ollama.com and download the installer for your operating system. Follow the installation instructions provided on the website. ✅ Step 2: Install an LLM ModelAfter installing Ollama, open your terminal or command prompt and run the following command to install a model: For example, to install qwen:1.8b, run:
Once installed, RAGGIN will be able to use the selected model to generate accurate and contextual responses locally. Here's a more polished and professional version of your installation guide: 🐳 RAGGIN Docker Installation GuideTo make RAGGIN work properly, ensure that Docker is installed and running on your system. You can follow the official installation guide here: 🔹 Quick Setup via DockerTo get started immediately with RAGGIN, simply pull the Docker image: 🔹 Customize LocallyIf you wish to modify or explore the source code, you can clone the repository: Then, use this command to run docker: 🧩 RAGGIN VS Code Extension Installation GuideTo install the RAGGIN extension in Visual Studio Code:
Once installed, the extension will automatically connect to your local RAGGIN backend and Ollama, allow you to interact with the Next.js assistant directly from your editor. You can install any supported version of Next.js directly through the extension, ensuring that your queries are answered with version-accurate information. 📊 Performance BenchmarksThe performance of RAGGIN may vary depending on the user's hardware capabilities. Larger LLMs typically require a more powerful GPU to run efficiently. For optimal results, consider using a model that matches your system's resources. Below is a summary of performance benchmarks we evaluated to help you choose a suitable configuration based on your system's capabilities. These results provide insights into how different models perform under various hardware setups:
🤝 Contributors |