OpenAI has announced new updates to its API for assistants, an API that enables developers to embed AI-powered assistants in their applications.

The API now includes a file search tool that allows searching of up to 10,000 files per assistant and can allow developers to integrate knowledge extraction into their assistants. It works with OpenAI’s vector repository objects.

The company also introduced new controls for setting the maximum input and output token so that developers can more directly limit costs. They can also now choose how many last messages will be used for context shortening.

Other new features include the introduction of the Tool Choice option, which allows the selection of a relevant tool. Other updates in this release include more model configuration settings, new streaming and polling utilities, support for fine-tuned models, and more.