Langgraph contd..

Lets interact with llms using langgraph and also our tools

• For today our tools will be simple python functions Refer Here

• In Langgraph tools are functions or external APIS that LLM can call as part of workflow or graph node.

• Tools extend the LLM capabilities beyond just generating,
• In a simplest form a tool is a function
• Best way to define a tool

from langchain.agents.tools import tool
@tool
def add_numbers(a: int, b: int) -> int:
    """Add two numbers and return the result"""
    return a + b

• @tool: decorator that registers the function as Langchain Tools

• A tool is just a special object of python with:

  • name
  • description
  • callable function
• In Langgraph, Each node represents a computation step and a common type of node is one that uses a tool

• We can integrate tools inside Langgraph using

  • An LLM that decides which tool to call
  • A tool executer that executes the tool
  • A langgraph node that wraps this logic

• Binding tools to llm

• using tools
• ToolNode