How does OpenAI Function Calling work?

preview_player
Показать описание
In this video, we're going to dig into OpenAI function calling. We'll explore what's happening under the hood before working through an example of how to use it to call a Weather API to see how warm (or not!) it is right now.

#llms #openai #functioncalling

Рекомендации по теме
Комментарии
Автор

The best simple explanation I have found about Function Calling. Thanks for making it so easy to understand!

AlexX-xtimes
Автор

I have several functions implemented in my project, each responsible for a specific task. However, frequently, when the user requests the extraction of information that should trigger function A, other functions (like B or C) are called instead. Although function A is correctly triggered on some occasions, this does not happen consistently. Why is this happening? I am using OpenAI's GPT-4 model.

michaelvilarino
Автор

Thanks for the great explanation :)
I have one query: How many API calls does it support? like in AWS it supports 5 APIs per agent (Bedrock)

rahulagalcha-rskg
Автор

As a developer, this is great. Thanks for clarifying right at the beginning that its us who have to make the function call and 👍 to the sequence diagram.

bibstha
Автор

For real AI, I don't think prompt engineering is needed. So that brings a question: are those GPTs real AI?

GG-uzus
Автор

i had to set the your speech rate to 0.75 in order for me to catch up with you, lol
thank you, very good explanation sir

abderahimmazouz
Автор

Your video is the best. I am just wondering " is there any way to set the fixed number of items in an array from an open ai reponse" when you using function calling

vuquangtruong
Автор

if I have multiple functions how does the
"for tool_call in tool_calls" loop work with different functions? the function_response parameter has the latitude and longitude hardcoded as arguments. what if my other functions deal with other stuff and don't require lat and long as arguments, but other arguments? I'm really confused by that bit. If I have more functions do I just add a "match case" check to pass the correct arguments for each function?

vladimirnicolescu
Автор

How did you get the longitude and latitude to pass to the function ? Was it in response by the LLM ?

amanvojha
Автор

Hi mark. I have an array of about 60 objects. Each object has a length property with a non null value. Each object has a text property with a null value. I've been trying for weeks after work to craft a prompt that will force OpenAI to generate a word - any english word for now - that has a character amount equal to the length property. I have about an 80% error rate - Rarely can it generate a word with characters equal to the length value. The error rate goes down to about 60% when I say it doesn't have to be a word. Do you feel that this function calling double API request is the only way to fix this issue to guarantee 100% success rate? thanks.

chriswooohoo
Автор

very clear introduction for open AI function calls
this video is super useful for me to understand function calls.

chenghung
Автор

Couldn't we do the same approach with LangChain's Agents?

fullstackai
Автор

then why langchain agents?
get more control by using openai function calling

RanaAnas-sh
Автор

Perfect explanation, all other videos were long winded

jorgesanabria
Автор

Why the fuck is everybody on the web giving just this weather example?
Can't you be more creative and authentic?
What the hell do I do if for example I need to translate an array of strings and always return a consistent and formated result?

imnbsp