Subject
- #LLM
- #Function Call
- #AI
- #Multi-Agent
- #RAG
Created: 2025-03-04
Created: 2025-03-04 21:53
The hottest keyword in the industry these days is LLM.
Models like Claude 3.5 and Grok3 are constantly emerging,
and services utilizing LLMs, such as뤼튼 (Ruiton) and Zeta, are also increasing.
As developers, we'll likely integrate LLMs into our services someday,
so it's a good idea to familiarize ourselves with the basic concepts beforehand to avoid confusion!
So, I've summarized the key keywords.
Simply put, LLM (Large Language Model) is
"an AI that understands text input and responds with text."
Models like GPT-4, Claude 3, and Grok3 are prime examples.
These days, LLMs go beyond simply generating sentences,
performing various tasks such as coding, image analysis, and solving equations.
It seems we've entered an era where developers utilize AI as a tool.
LLMs don't just provide answers; they can also be instructed to
"call the necessary tools to assist with the task."
For example,
However, the LLM itself doesn't directly call the API;
we need to implement the actual call in code ㅜㅜ
No matter how intelligent an LLM is,
it generates answers based only on the data it has been trained on.
So, how does it retrieve information like the latest news or internal documents?
That's whereRAGcomes in.
This allows the LLM to incorporate up-to-date information.
In short, before the LLM answers, it's fed the necessary materials for the answer, and the summarization or answering based on those materials is all called
RAG.
When you look at LLM models, you'll see numbers like 8B and 70B attached.
This refers to thenumber of parameters (Parameter) the model has been trained on.
Larger models are more accurate, but speed and cost can be a burden.
These days, effectively utilizinglightweight modelsis a trend.
Heavier models result in slower response times,
leading to higher churn rates among end-users.
Instead of an LLM handling everything alone,
multiple smaller AIs (agents) work collaboratively.
For example:
Dividing roles like this results infaster speeds and more accurate responses.
Isn't it just like a company? Someone handles the frontend... someone handles the backend...
LLMs don't always give the right answer.
They might provide incorrect answers.
Therefore,Validation Feedbackis necessary.
This can be automated to createa self-learning system for the LLM.
Or, when Function Call or response format is defined,
if it doesn't follow the format, it can be forced to follow it.
To actually use Function Call with OpenAI's GPT-4,
it can be implemented as follows.
🔹 TypeScript Example
By using Function Call in this way,
LLMs can evolve into a **"truly useful AI"** that performs actual functions, rather than just generating text.
Carefully filling in argument values for these Function Calls can be quite tedious.
Therefore, services like Vercel AI and LangChain use the zod library to
perform Validation Feedback on whether the argument values returned by the LLM are correct.
This ensures highly accurate Function Calls.
However, writing schemas for each argument of complex functions using zod can be very cumbersome, and
developers might find it"tedious".
Therefore, I recommend theAgenticalibrary.
With this simple code, functions in three classes and swagger endpoints are
designated as Function Calls and automatically called during conversations.
This creates a simple"chatbot agent".
The field of handling LLMs and AI is becoming increasingly user-friendly.
The advancement of technology is truly awe-inspiring.
Comments0