langgraph/docs/docs/how-tos/index.md

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 out AI workflows, with special focus placed on ReAct-style agents with tool calling.

• ReAct agent: How to create a tool-calling agent that Reasons and Acts to accomplish tasks
• Persistence: How to give your graph "memory" and resilience 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
• Map-reduce: How to branch different views of the state for parallel node execution (even applying the same node in parallel N times)
• 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
• Pass run time values to tools: Pass values that are only known at run time to tools (e.g., the ID of the user who made the request)
• Dynamic direct return: Let the LLM 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

Structured output

• Extraction with re-prompting: How to generate complex nested schemas using JSONPatch retries, for when function calling is insufficient, and regular reprompting still fails to generate valid results