LangGraph

LangGraph is an OSS library for building stateful, multi-actor applications with LLMs, specifically designed for agent and multi-agent workflows. The framework supports critical agent architecture features including persistent memory across conversations and human-in-the-loop capabilities through checkpointed states.

Installing Libraries

pip install -U langgraph langchain-together

Set your Together AI API key:

export TOGETHER_API_KEY=***

Example

In this simple example we augment an LLM with a calculator tool!

import os
from langchain_together import ChatTogether

llm = ChatTogether(model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
                   api_key=os.getenv("TOGETHER_API_KEY"))

# Define a tool
def multiply(a: int, b: int) -> int:
    return a * b

# Augment the LLM with tools
llm_with_tools = llm.bind_tools([multiply])

# Invoke the LLM with input that triggers the tool call
msg = llm_with_tools.invoke("What is 2 times 3?")

# Get the tool call
msg.tool_calls

Next Steps

📘

LangGraph - Together AI Notebook

Learn more about building agents using LangGraph with Together AI in our:

• Agentic RAG Notebook
• Planning Agent Notebook