Function calling in LLMs in Agentic AI - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is function calling in Large Language Models (LLMs)?

Function calling in LLMs is when the model generates a request to run a specific function or API based on the user's input, allowing the model to interact with external tools or perform tasks beyond text generation.

beginner

Why do LLMs use function calling?

LLMs use function calling to extend their capabilities by connecting to external services or code, enabling them to perform actions like fetching real-time data, calculations, or controlling devices, which they cannot do by text generation alone.

intermediate

How does an LLM decide which function to call?

The LLM analyzes the user's input and context, then selects the most relevant function from a predefined list based on the task or query, generating a structured call with parameters for that function.

intermediate

What is the role of function parameters in LLM function calling?

Function parameters provide the necessary details or inputs the function needs to execute correctly. The LLM fills these parameters based on the user's request to ensure the function performs the intended action.

beginner

Give an example of a simple function call generated by an LLM.

For example, if a user asks "What's the weather in Paris?", the LLM might generate a function call like getWeather(city="Paris") to fetch current weather data from an external API.

What does function calling in LLMs enable the model to do?

A Interact with external tools or APIs

B Generate longer text responses

C Improve grammar accuracy

D Reduce model size

Function calling allows LLMs to interact with external tools or APIs to perform tasks beyond text generation.

Which of the following is NOT a reason for using function calling in LLMs?

A Train the model faster

B Access real-time data

C Perform calculations

D Control external devices

Function calling does not affect training speed; it extends model capabilities by connecting to external functions.

How does an LLM know which function to call?

A Random selection

B Based on user input and context

C User manually selects the function

D Functions are called in alphabetical order

The LLM analyzes user input and context to select the most relevant function.

What information does the LLM include when calling a function?

A Function name only

B Model weights

C Function name and parameters

D Only parameters

The LLM generates the function name along with the necessary parameters for execution.

Which example shows a correct function call generated by an LLM?

A callAPI('Paris')

B weatherParis()

C fetchData(city=Paris)

D getWeather(city="Paris")

The function call getWeather(city="Paris") clearly shows the function name and parameter in a structured way.

Explain in your own words what function calling in LLMs means and why it is useful.

Think about how LLMs can do more than just generate text by asking other programs to help.

Describe the process an LLM follows to generate a function call from a user question.

Consider the steps from reading the question to creating the function request.