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.
FileMaker is a database system that can be adapted extremely well to individual company requirements thanks to its flexible interfaces. Data can be imported from almost any other database and from Office applications such as Microsoft Excel, Word or Apple Numbers. FileMaker databases can be run on Windows or Mac OS X computers, the iPad, iPhone and iPod touch, making them ideal for mobile data collection. This article explains how a new project for the development of a FileMaker database works, which requirements should be met and what you can do yourself to prepare a development project.
In another presentation at the FileMaker Conference 2012, I showed ways to optimize screen layouts and navigation within a FileMaker solution. First, I provided an overview of the methods and technologies that can be used to implement database-supported navigation in FileMaker. In a short excursion into GUI studies, I show how a graphical user interface should look and be structured according to the current scientific state of the art. Finally, using a practical example, I show how database-supported navigation can be implemented in a FileMaker solution with pure on-board resources without plug-ins.