Function calls, in the context of AI models like large language models (LLMs), refer to the ability of the model to invoke external functions or APIs to gather information or perform actions. Instead of just generating text, the LLM can generate a structured output (often JSON) that specifies which function should be called, along with the necessary parameters. A separate system then executes the function and returns the result to the LLM, which can then incorporate the result into its response. This expands the LLM's capabilities beyond its pre-trained knowledge, enabling it to interact with the real world, access up-to-date information, and automate tasks.
This tech insight summary was produced by Sumble. We provide rich account intelligence data.
On our web app, we make a lot of our data available for browsing at no cost.
We have two paid products, Sumble Signals and Sumble Enrich, that integrate with your internal sales systems.