Previously, we have discussed why you may be interested in leveraging local LLMs for to keep data private , how to get started with integrating Claris FileMaker with Ollama and a brief discussion of the trade offs between using the different text generative LLMs (Llama vs DeepSeek). The common thread will all these articles is that these are LLMs optimised for processing text prompt inputs to generate text outputs. However, the Ollama site also provides models that support vision processing , including Gemma3, LlaVA and llama3.2-vision. Impressively, vision processing is still viable using modest Apple Silicon Mac using the llama3.2-vision model. A quick reminder - Why run local AI models on your Mac? Running local LLMs gives you: Full data privacy – your data stays on your machine. No cloud dependency – perfect for secure or offline environments. Faster response times – no network latency. Cost control – no pay-per-query billing. Development feasibility testing - quick prototyping to provide the efficiency of the AI assisted workflow and the fit of different models for your application. Whether you’re in healthcare, legal services, finance, or manufacturing, private AI lets you leverage powerful automation without compromising data compliance or sovereignty. Setting Up llama3.2-vision integration with Claris FileMaker 1. Choose the Right Model The llama3.2-vision build weighs in at 7.8GB and runs with reasonable performance on an entry level M3 class MacBook Air with 24GB RAM. The more advanced 'multimodal' llama4 weighs in at 67GB by comparison - good luck running that with anything less than the 128GB+ RAM configurations of the M2/M3 Ultra or M4 Pro variants. 2. Download and Install Ollama 👉 Download here: https://ollama.com/download Move Ollama.app into your Applications folder Open the app and approve any permissions (including full disk access if prompted). 3. Run Your First Model Open Terminal and run: ollama run llama3.2-vision 4. Check the Server Is Running Open a web browser and go to: http://localhost:11434/ If everything is configured correctly, you should see “Ollama is running” in your web browser page. If not, check your local firewall and security settings to ensure port 11434 is open and accessible. Connecting llama3.2-vision with FileMaker Pro The process for integrating is identical to the text model as a starting point, but the image needs to be converted to Base64 text encoding to send in an additional parameter in the JSON format (" images"; ['imageInBase64'] ). The simplest way to do this within FileMaker is to save your image into a Container field and then convert that using FileMaker's built in Base64Encode() function (this could be stored in a temporary variable or a calculation field as in this example below):

Discover the power of DeepSeek R1—an efficient, open-source AI model ideal for private, local deployment using Ollama and Apple Silicon. Learn how DeepSeek compares to LLaMA, Mistral, and other LLMs in real-world applications, and explore how it integrates seamlessly with Claris FileMaker for secure, on-premise AI automation. Ideal for businesses needing low-cost, high-performance, and fully private AI solutions.

Claris has added dozens of new features with each release of FileMaker - so many that it is hard to quickly see exactly how you might quickly benefit from updating. Here we summarise some of our favourite features we like to highlight to customers looking to upgrade:

Discover why FileMaker is a cost-effective, flexible LIMS solution for 2025—ideal for labs needing secure, customisable, and rapidly deployable systems.

Learn how to run private AI locally using Ollama and integrate it with Claris FileMaker. Discover step-by-step setup, model recommendations, and how to build secure, AI-powered workflows without sending data to the cloud. Perfect for businesses prioritising data privacy and compliance.

Integrate Claris FileMaker with local LLMs like LLaMA 3 to boost efficiency with AI—without risking data privacy. Secure, intelligent automation for your business

Still running your business on Google Sheets? Spreadsheets are great—until they start holding you back. If you’re managing complex processes, critical data, or multiple users through Google Sheets, it’s time to upgrade.

The Claris FileMaker Server 21.1.4 update is now available and includes important fixes that address known issues from previous versions: Key Fixes 1. Field definitions incorrectly read from cache. A bug introduced in version 21.0 caused field definitions to be incorrectly cached, resulting in symptoms such as: Empty related fields Missing value lists and indexes “Insufficient privileges (error -9)” messages 2. Windows only: Server-side script sessions limited by CPU cores. Version 21.1.3 limited simultaneous server-side script sessions to the number of CPU cores on Windows. This impacted I/O-bound environments by unnecessarily queuing sessions. 21.1.4 resolves this by allowing up to 50 concurrent script sessions on Windows before queueing begins—regardless of CPU cores. These sessions may be triggered by schedules, OData, or Perform Script on Server (PSoS). Note: This behavior is not controlled by the AllowPSoS setting. Claris Recommends: To ensure system stability, it is advised to limit active clients to 40 - 45 simultaneous sessions. Exceeding 50 may result in delays, memory overload, or session hangs. Do you need assistance with upgrading? DataTherapy are pleased to announce that Claris FileMaker 2024 (version 21.1) managed private cloud hosting packages are immediately available. DataTherapy can provide scalable, managed FileMaker packages for businesses of all size. Full details of all of our packages can be found here . We can offer a range of a variety of enhanced options such as domain management, custom SSL certificates, VPN, VLAN, disaster recovery and integration with other technologies. If you need additional information on upgrading to the new release, advise on how to migrate your current on-premises FileMaker Server to the cloud, or would like to arrange a free trial of any of our packages then please don’t hesitate to contact our team .

Using Microsoft Excel for workflows and complex data management instead of a dedicated database presents several inherent problems. These issues stem from Excel’s limitations in scalability, data integrity, collaboration, automation, and security. Below is a detailed breakdown of these challenges and how a custom Claris FileMaker App can meet these challenges . . .