mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-09-30 05:25:05 +02:00
1.9 KiB
1.9 KiB
hide
| hide | |
|---|---|
|
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 (agents that Reason and Act to accomplish tasks).
- How to create a ReAct agent
- How to add persistence ("memory") to your graph
- How to view and update graph state
- How to run graph asynchronously
- How to stream graph responses
- How to visualize your graph
- How to add runtime configuration to your graph
Design patterns
Recipes showing how to apply common design patterns in your workflows:
- How to create subgraphs
- How to create branches for parallel execution
- How to create map-reduce branches for parallel execution
- How to add human-in-the-loop
The following examples are useful especially if you are used to LangChain's AgentExecutor configurations.
- How to force an agent to call a tool
- How to pass runtime values to tools
- How to let agent return tool results directly
- How to have agent respond in structured format
- How to manage agent steps