Just published a short practical video where I run RAG completely offline on my own laptop using Ollama.
No cloud, no API keys, no data leaving the machine.
In the video I show:
Setting up local RAG
Keeping everything private
Avoiding the usual hallucination issues that happen with closed-book models
Video: https://youtu.be/BnTr9Vf255Y?si=5Nr6PvuYJdYw9uAv
GitHub:https://github.com/AI-Literacy-Lab/localrag
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](https://youtu.be/BnTr9Vf255Y)
Top comments (0)