In an increasingly confusing world of information, it is becoming more and more important to make your own databases searchable in a targeted manner - not via classic full-text searches, but through semantically relevant answers. This is exactly where the principle of the RAG database comes into play - an AI-supported search solution consisting of two central components:
Ollama
Posts about Ollama, a platform for local AI models. Here you will find instructions, experiences and tips for everyday and business use.
Ollama meets Qdrant: A local memory for your AI on the Mac
Local AI with memory - without cloud, without subscription, without detour
In a previous articles I explained how to configure Ollama on the Mac install. If you have already completed this step, you now have a powerful local language model - such as Mistral, LLaMA3 or another compatible model that can be addressed via REST API.
However, the model only "knows" what is in the current prompt on its own. It does not remember previous conversations. What is missing is a memory.
Local AI on the Mac: How to install a language model with Ollama
Local AI on the Mac has long been practical - especially on Apple-Silicon computers (M series). With Ollama you get a lean runtime environment for many open source language models (e.g. Llama 3.1/3.2, Mistral, Gemma, Qwen). The current Ollama version now also comes with a user-friendly app that allows you to set up a local language model on your Mac at the click of a mouse. In this article you will find a pragmatic guide from installation to the first prompt - with practical tips on where things traditionally go wrong.