Inferencer v1.7 with custom tool calls

In version 1.7.0 the models now come to life with the custom tool calls framework.

Tools Editor

The tools editor allows you to enable built-in tools such as ‘get_webpage_content' so that the models can use them when needed. For example, if you'd like a webpage or search result inferenced, simply enable the tool in the Tools section, and allow tool calls in the chat settings panel.

P.S. If you find Inferencer useful, please consider leaving a review on the App store, it would be much appreciated.

Custom Tools

With the tools editor you can also provide your own custom set of tools available for the model to use, all running inside a verified sandboxed environment. This ensures that access to files outside the application folders is blocked by the operating system. If you’re ever unsure whether an app is truly sandboxed, just try asking a model for help, you may be surprised by some apps’ claims and the actual results.

Please note that this is a new feature, so if you run into any issues or would like any particular tools provided out of the box, please let us know.

More improvements

As always, if you have any features or suggestions you’re more than welcome to add them to our public roadmap.

Thanks again for your support, and as a reminder, all AI processing is done offline, directly on your devices. No telemetry, no background "update" checks.