Agentic orchestration with LangGraph

Make sure to first run the cell to install the libraries

• Construct a State class to create a message history where new messages are appended to it, and use it to create a graph state.
• Define a gpt-4o-mini LLM using the ChatOpenAI class, and a function called llm_node() to invoke it on state messages and store the result.
• Construct and compile a graph that routes the input into an LLM node, which calls llm_node, and returns the result.
• Run the code provided to visualize the graph and talk to your agent!

---

Note: If you’re running DataLab in Restricted Mode, this exercise isn’t supported yet. We’re actively working on making it available in the future.

---