𝗦𝗲𝘁𝘂𝗽 𝗔 𝗟𝗼𝗰𝗮𝗹 𝗔𝗜 𝗥𝗔𝗚 𝗦𝘆𝘀𝘁𝗲𝗺 𝗪𝗶𝗍𝗵 𝗝𝗲𝗧𝗕𝗿𝗮𝗶𝗻𝘀 𝗜𝗗𝗘 𝗜𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗶𝗼𝗻

𝗦𝗲𝘁𝘂𝗽 𝗔 𝗟𝗼𝗰𝗮𝗹 𝗔𝗜 𝗥𝗔𝗚 𝗦𝘆𝘀𝘁𝗲𝗺 𝗪𝗶𝗍𝗵 𝗝𝗲𝗧𝗕𝗿𝗮𝗶𝗻𝘀 𝗜𝗗𝗘 𝗜𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗶𝗼𝗻 You want to adopt a new technology or workflow. The hardest part is getting started.

• You search for answers
• You find a lot of fake AI generated content
• You need actual human experience

I will share my setup with you. You can adapt each step to your preferences.

• All software is free and open source
• It runs locally

Here's what you need:

• Windows
• Docker (optional)
• Free and open source software

To get started:

• Open a PowerShell terminal
• Run the command: irm https://ollama.com/install.ps1 | iex
• Ollama is a free application for downloading and running LLMs locally
• Use the command: ollama run gemma4 to download and run Gemma4
• Test it by opening http://127.0.0.1:11434

To get a local web UI:

• Use Open WebUI
• Run the Docker command: docker run -d -p 3000:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:cuda
• Access the web UI at http://127.0.0.1:3000

To integrate with JetBrains IDE:

• Open your settings
• Go to Tools > AI Assistant > Providers & API Keys
• Select Ollama as the provider
• Enter the URL to your locally running ollama instance
• Click on Test Connection

That's it! Remember to start ollama and load your local LLM model before using it in your IDE. Source: https://dev.to/nikolastojilj12/quick-and-easy-local-ai-rag-setup-with-jetbrains-ide-integration-and-browser-ui-bh8