mirror of
https://github.com/langchain-ai/langgraph.git
synced 2026-09-03 08:18:47 +02:00
Eugene YurtsevandGitHub
200c09b662
- Turn on strict mode to fail docs build if there are any internal broken anchor links. - Fix broken anchor links. - Delete storm tutorial that has fake markdown inside it (we'll figure out how to deal with it later)
1.5 KiB
1.5 KiB
search, tags, hide
| search | tags | hide | ||||||
|---|---|---|---|---|---|---|---|---|
|
|
|
Human-in-the-loop
LangGraph supports robust human-in-the-loop (HIL) workflows, enabling human intervention at any point in an automated process. This is especially useful in large language model (LLM)-driven applications where model output may require validation, correction, or additional context.
Key capabilities
-
Persistent execution state: LangGraph checkpoints the graph state after each step, allowing execution to pause indefinitely at defined nodes. This supports asynchronous human review or input without time constraints.
-
Flexible integration points: HIL logic can be introduced at any point in the workflow. This allows targeted human involvement, such as approving API calls, correcting outputs, or guiding conversations.
Typical use cases
- 🛠️ Reviewing tool calls: Humans can review, edit, or approve tool calls requested by the LLM before tool execution.
- ✅ Validating LLM outputs: Humans can review, edit, or approve content generated by the LLM.
- 💡 Providing context: Enable the LLM to explicitly request human input for clarification or additional details or to support multi-turn conversations.
Implementation
interruptfunction: Pauses execution at a specific point, presents information for human review.Commandprimitive: Used to resume execution with a value provided by the human.