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.

Practice

1. What is the main purpose of function calling in large language models (LLMs)?

easy

A. To prevent the LLM from understanding user questions

B. To let the LLM run specific external functions and get precise results

C. To slow down the LLM's response time intentionally

D. To make the LLM generate random text without any control

Solution

1. Step 1: Understand function calling role

   Function calling lets LLMs connect to external code or tools to perform tasks.

2. Step 2: Identify the main benefit

   This connection helps LLMs provide accurate, task-specific answers by running real functions.

3. Final Answer:

   To let the LLM run specific external functions and get precise results -> Option B

4. Quick Check:

   Function calling purpose = precise external function use [OK]

Hint: Function calling means running real code from the LLM [OK]

Common Mistakes:

• Thinking function calling makes LLMs slower
• Believing it causes random text generation
• Assuming it blocks understanding questions

2. Which of the following is the correct way to specify a function call in an LLM prompt?

easy

A. {"name": "get_weather", "parameters": {"city": "Paris"}}

B. function_call: get_weather(city='Paris')

C. call_function('get_weather', city='Paris')

D. run get_weather with city=Paris

Solution

1. Step 1: Recognize JSON format for function calls

   LLMs use structured JSON to specify function names and parameters clearly.

2. Step 2: Match the correct JSON syntax

   {"name": "get_weather", "parameters": {"city": "Paris"}} shows a JSON object with "name" and "parameters", which is the standard format.

3. Final Answer:

   {"name": "get_weather", "parameters": {"city": "Paris"}} -> Option A

4. Quick Check:

   Function call format = JSON object [OK]

Hint: Function calls in LLMs use JSON with name and parameters [OK]

Common Mistakes:

• Using plain text instead of JSON
• Trying to call functions like regular code
• Missing quotes around keys or values

3. Given this function call JSON sent to an LLM:

{"name": "calculate_sum", "parameters": {"a": 5, "b": 3}}

What should the LLM do next?

medium

A. Return the sum 8 as the function output

B. Ignore the function call and generate unrelated text

C. Ask the user to provide values for a and b

D. Throw an error because parameters are missing

Solution

1. Step 1: Understand the function call content

   The JSON specifies a function named "calculate_sum" with parameters a=5 and b=3.

2. Step 2: Determine expected LLM behavior

   The LLM should run the function with these inputs and return the result, which is 8.

3. Final Answer:

   Return the sum 8 as the function output -> Option A

4. Quick Check:

   Function call with inputs = output sum 8 [OK]

Hint: LLM runs function with given inputs and returns result [OK]

Common Mistakes:

• Ignoring the function call and chatting instead
• Requesting inputs already provided
• Assuming missing parameters cause errors

4. You wrote this function call JSON for an LLM:

{"name": "get_user_info", "params": {"user_id": 42}}

Why might the LLM fail to execute this call?

medium

A. Because the function name must be uppercase

B. Because user_id must be a string, not a number

C. Because the key should be "parameters", not "params"

D. Because the JSON is missing a closing brace

Solution

1. Step 1: Check JSON keys for function calling

   The standard key for parameters is "parameters", not "params".

2. Step 2: Identify why LLM fails

   Using "params" means the LLM won't recognize the inputs and can't run the function.

3. Final Answer:

   Because the key should be "parameters", not "params" -> Option C

4. Quick Check:

   Correct key = "parameters" [OK]

Hint: Use "parameters" key exactly in function call JSON [OK]

Common Mistakes:

• Using "params" instead of "parameters"
• Assuming number types cause failure
• Thinking function names must be uppercase

5. You want to build a chatbot that can book appointments by calling an external scheduling function. Which approach best uses function calling in LLMs to achieve this?

hard

A. Ask the user to book appointments manually without automation

B. Make the LLM guess appointment times without calling any function

C. Hardcode all appointment slots inside the LLM prompt text

D. Define a function schema with name and parameters, let LLM call it with user inputs, then run the real scheduler

Solution

1. Step 1: Understand chatbot function calling design

   Function calling lets the LLM decide when to call the scheduler with user data.

2. Step 2: Choose best integration method

   Defining a function schema and letting the LLM call it dynamically is the correct approach.

3. Final Answer:

   Define a function schema with name and parameters, let LLM call it with user inputs, then run the real scheduler -> Option D

4. Quick Check:

   Function calling enables dynamic external task calls [OK]

Hint: Use function schema and let LLM call real scheduler [OK]

Common Mistakes:

• Ignoring function calling and guessing answers
• Hardcoding data inside prompt text
• Not automating booking at all