Handling different States

• Langgraph is basically designed to work with one state type. i.e. input and output should be of same type.
• This means we can have different intermediate state.
• Number guessing game
  • State: input as well as output
    • guessed_number
    • result
  • intermediate state
    • guessed_number
    • result
    • count
    • picked_number

React agents

• This concept was introduced as a research paper
  

• Lets create a simple React Agent from langgraph Refer Here

• Now agents would require to remember previous interactions, To deal with this langraph has persistence which revolves around

  • checkpoint
  • thread
  • memory
• Note: High level overview of Integrating langgraph with existing apps