Merge pull request #2702 from langchain-ai/eugene/update_more_docs

eugene/update more docs
This commit is contained in:
Eugene Yurtsev
2024-12-10 21:18:49 -05:00
committed by GitHub
3 changed files with 8 additions and 8 deletions
@@ -10,7 +10,7 @@
"\n",
"!!! note\n",
"\n",
" Current recommended way to add dynamic breakpoints is using [`interrupt()`][langgraph.types.interrupt] API. See this [how-to guide](../interrupt) to learn more.\n",
" For **human-in-the-loop** workflows use the new [`interrupt()`](../../../reference/types/#langgraph.types.interrupt) function for **human-in-the-loop** workflows. Please review the [Human-in-the-loop conceptual guide](../../../concepts/human_in_the_loop) for more information about design patterns with `interrupt`.\n",
"\n",
"!!! tip \"Prerequisits\"\n",
"\n",
@@ -18,7 +18,6 @@
"\n",
" * [Breakpoints](../../../concepts/breakpoints)\n",
" * [LangGraph Glossary](../../../concepts/low_level)\n",
" \n",
"\n",
"Human-in-the-loop (HIL) interactions are crucial for [agentic systems](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/#human-in-the-loop). [Breakpoints](https://langchain-ai.github.io/langgraph/concepts/low_level/#breakpoints) are a common HIL interaction pattern, allowing the graph to stop at specific steps and seek human approval before proceeding (e.g., for sensitive actions).\n",
"\n",
@@ -438,7 +437,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
"version": "3.11.4"
}
},
"nbformat": 4,
@@ -11,14 +11,15 @@
"tags": []
},
"source": [
"# How to use add breakpoints using interrupt?\n",
"# How to use interrupt for human-in-the-loop?\n",
"\n",
"!!! tip \"Prerequisits\"\n",
"!!! tip \"Prerequisites\"\n",
"\n",
" This guide assumes familiarity with the following concepts:\n",
"\n",
" * [Breakpoints](../../../concepts/breakpoints)\n",
" * [LangGraph Glossary](../../../concepts/low_level)\n",
" * [Interrupt](../../../concepts/low_level#interrupt)\n",
" * [Command](../../../concepts/low_level#command)\n",
" \n",
"\n",
"An `interrupt` is a convenient way to support human-in-the-loop workflows.\n",
+2 -2
View File
@@ -48,12 +48,12 @@ LangGraph makes it easy to manage conversation [memory](../concepts/memory.md) i
[Human-in-the-loop](../concepts/human_in_the_loop.md) functionality allows
you to involve humans in the decision-making process of your graph. These how-to guides show how to implement human-in-the-loop workflows in your graph.
- [How to add breakpoints](human_in_the_loop/breakpoints.ipynb)
- [How to add dynamic breakpoints](human_in_the_loop/dynamic_breakpoints.ipynb)
- [How to edit graph state](human_in_the_loop/edit-graph-state.ipynb)
- [How to wait for user input](human_in_the_loop/wait-user-input.ipynb)
- [How to view and update past graph state](human_in_the_loop/time-travel.ipynb)
- [How to review tool calls](human_in_the_loop/review-tool-calls.ipynb)
- [How to add static breakpoints](human_in_the_loop/breakpoints.ipynb): Use for debugging purposes. For [**human-in-the-loop**](../concepts/human_in_the_loop.md) workflows, we recommend the [`interrupt()`](../../../reference/types/#langgraph.types.interrupt) function instead.
- [How to add dynamic breakpoints with `NodeInterrupt`](human_in_the_loop/dynamic_breakpoints.ipynb): **Not recommended**: Use the [`interrupt` function](../concepts/human_in_the_loop.md) instead.
### Streaming