Langgraph integration with livekit

Thanks for reaching out, giri. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.

Can we integrate langgraph with livekit?

Absolutely, you can integrate LangGraph with LiveKit! It’s pretty straightforward using the LiveKit LangChain plugin, which lets you run LangGraph workflows as large language models (LLMs) right inside LiveKit’s AI agents framework. If you’d like, I’m here to help with the detailed steps or any questions you have about getting it set up. Just give me a shout!

Give a sample code for integration

Hey there! Here’s a handy little code snippet to help you integrate LangGraph with LiveKit:

from langgraph.graph import StateGraph
from livekit.agents import AgentSession, Agent
from livekit.plugins import langchain

# Define and compile your LangGraph workflow
def create_workflow():
    workflow = StateGraph()
    # Add your nodes and edges to the workflow
    return workflow.compile()

# Create an AgentSession with the LangGraph workflow
session = AgentSession(
    llm=langchain.LLMAdapter(graph=create_workflow()),
    # Add other configurations like stt, tts, vad, turn_detection, etc.
)

# Use the session as needed in your application
print("LangGraph integrated with LiveKit successfully!")

This snippet shows you how to set up a LangGraph workflow, compile it, and plug it into a LiveKit AgentSession as an LLM. Feel free to tweak the workflow and session settings to fit exactly what you need. If you have any questions or want to chat more about it, I’m here to help!