How-To Guides¶
Welcome to the LangGraph How-To Guides! These guides provide practical, step-by-step instructions for accomplishing key tasks in LangGraph.
Core¶
The core guides show how to address common needs when building a out AI workflows, with special focus placed on ReAct-style agents with tool calling.
- Persistence: How to give your graph "memory" and resiliance by saving and loading state
- Time Travel: How to navigate and manipulate graph state history once it's persisted
- Async Execution: How to run nodes asynchronously for improved performance
- Streaming Responses: How to stream agent responses in real-time
- Visualization: How to visualize your graphs
- Configuration: How to indicate that a graph can swap out configurable components
Design Patterns¶
Recipes showing how to apply common design patterns in your workflows:
- Subgraphs: How to compose subgraphs within a larger graph
- Branching: How to create branching logic in your graphs for parallel node execution
- Human-in-the-Loop: How to incorporate human feedback and intervention
The following examples are useful especially if you are used to LangChain's AgentExecutor configurations.
- Force Calling a Tool First: Define a fixed workflow before ceding control to the ReAct agent
- Dynamic Direct Return: Let the LLM to decide whether the graph should finish after a tool is run or whether the LLM should be able to review the output and keep going.
- Respond in Structured Format: Let the LLM use tools or populate schema to provide the user. Useful if your agent should generate structured content.
- Managing Agent Steps: How to format the intermediate steps of your workflow for the agent.
Alternative ways to define State¶
- Pydantic State: Use a pydantic model as your state