LLM Function Calling - AI Tools Deep Dive

[@IdPreferNot1]

The BEST walkthrough and sample code on tool calling on KZbin!

[@therealsergio]

Adam, your content is very helpful and thoughtfully put together. It’s clear there are a lot of hours going into their preparation

[@terryliu3635]

The best walk through on this topic ever!! Thank you!!!

[@Alexfnplays]

crystal clear and right to the point!!!

[@sunitjoshi3573]

Nice video! I was just thinking about function calling…and your video showed up! Thanks 😊

[@AdamLucek]

Perfect!

[@PragyaKaushik-q8f]

This is amazing content! Quite concise and interesting! Thank you so much!!

[@JustinHennessy]

Amazing run down on tools. Thanks so much for sharing.

[@BagusSulistyo]

hi Adam, thank for video awesomeeeee !!

[@Horizont.]

Great video. Dude's been speaking nonstop for 30min straight. Now, I need a 2 hour break.

[@amk2298]

😂😂😂😂

[@Karthik-ln7eg]

great video. very clear explanation.

[@AdamLucek]

Thanks!

[@JimHeil]

Awesome video! Thank you!

[@AdamLucek]

Thanks!!!

[@sirishkumar-m5z]

An intriguing exploration into LLM function calling! Investigating further AI tools may improve your comprehension even more.

[@billblair3155]

U Da Man 😎

[@coolmcdude]

My favorite subject

[@chrisjhandy]

awesome video!

[@rowcolumn7499]

Thank you Adam and you effort to make this video. May I ask, in 2025, what is/are best tools if I want to develop an app that can do RAG and external tools calling in your opinion? llamaindex/langgraph/langchain? Thanks in advance!

[@skibidi-skibidi-bap]

Wait so does Langchain create the whole Json for you using the Tool decorator?

[@aishwaryaallada0925]

Awesome video! Is the code shared anywhere? 😊

[@AdamLucek]

Yes! In description and direct link here: github.com/ALucek/tool-calling-guide

[@youtubemensch]

How are possible with a LLM running on a own Server? So without an Ai-API. Like a Llama model. Is this possible with a specific model?

[@siddheshwarpandhare1698]

Hi Adam, well explained all content, I need to disable parallel calling, but I am not sure where to Put parallel_function_tool:false , can you help me in this case?

[@AdamLucek]

Sure, that's placed here with OpenAI's API response = client.chat.completions.create( model="gpt-4o", messages=messages, tools=first_tools, tool_choice="auto", parallel_tool_calls=False # parallel function calling ) or with Langchain during the bind_tools stage llm_tools = llm.bind_tools(tools, parallel_tool_calls=False)

[@siddheshwarpandhare1698]

@@AdamLucek Completions.create() got an unexpected keyword argument 'parallel_tool_calls' getting thsi error

[@AdamLucek]

I was getting that too then I updated my OpenAI api with pip and it fixed it! Make sure you restart your kernel after if you’re in a notebook environment

[@siddheshwarpandhare1698]

Thank you ​@@AdamLucek

[@DaleIsWigging]

The tutorial doesn't say how to insert your API key. To do this replace { client = OpenAI() } with : { import os from dotenv import load_dotenv # Load environment variables load_dotenv() client = OpenAI() # OpenAI API configuration client.api_key = os.getenv("OPENAI_API_KEY") } ignore the "{" and "}". Then you can use a .env file with: OPENAI_API_KEY="sk-proj..."

[@AdamLucek]

Also possible to do Import os os.environ["OPENAI_API_KEY"] = "your-api-key-here" And it will automatically pull the environment variable when creating the client etc. Thanks for pointing out!

[@gani2an1]

where can we see the functions that are available with each model?

[@maxpalmer8660]

Kinda hate this dudes voice ngl. Anyone else with me?

[@AdamLucek]

I been thinking this…

[@skibidi-skibidi-bap]

No. I am not with you.