Dive into langgraph

TypeDict

• dictionary

x = {
    'name': 'python',
    'version': 3.11
}

x['name']
# python

x['version']
# 3.11

• Type Dict

from typing_extensions import TypeDict
class Technology(TypeDict):
    name: str
    version: float

tech = Techonology(name='python', version=3.11)

Lets build a workflow with decision to make

• Overview
  

• conditional edge

• Refer Here for the changes

Adding LLMs to langgraph

• To interact with llms with langgraph we need to understand Messages. There are 5 types of messages on larger note
  • HumanMessage: This is your input to llm (prompt)
  • AIMessage: This is response from llm
  • SystemMessage
  • FunctionCallMessage
  • ToolMessage

GCloud CLI Setup

• Install gcloud cli
• login into gcloud gcloud auth login
• setup application auth login gcloud auth application-default login

Extra pip packages

• INstall langchain and langchain-core

pip install langchain-core langchain

• Install langchain google vertex

pip install -qU "langchain[google-vertexai]"

• Install openai (optional)

pip install -qU "langchain[openai]"