How to add breakpoints¶
When creating LangGraph agents, it is often nice to add a human-in-the-loop component. This can be helpful when giving them access to tools. Often in these situations you may want to manually approve an action before taking.
This can be in several ways, but the primary supported way is to add an "interrupt" before a node is executed. This interrupts execution at that node. You can then resume from that spot to continue.
Setup¶
First we need to install the packages required
%%capture --no-stderr
%pip install --quiet -U langgraph langchain_anthropic
Next, we need to set API keys for Anthropic (the LLM we will use)
import getpass
import os
def _set_env(var: str):
if not os.environ.get(var):
os.environ[var] = getpass.getpass(f"{var}: ")
_set_env("ANTHROPIC_API_KEY")
Optionally, we can set API key for LangSmith tracing, which will give us best-in-class observability.
os.environ["LANGCHAIN_TRACING_V2"] = "true"
_set_env("LANGCHAIN_API_KEY")
Build the agent¶
We can now build the agent. We will build a relatively simple ReAct-style agent that does tool calling. We will use Anthropic's models and a fake tool (just for demo purposes).
# Set up the tool
from langchain_anthropic import ChatAnthropic
from langchain_core.tools import tool
from langgraph.graph import MessagesState
from langgraph.prebuilt import ToolNode
from langgraph.graph import END, StateGraph
from langgraph.checkpoint.memory import MemorySaver
@tool
def search(query: str):
"""Call to surf the web."""
# This is a placeholder for the actual implementation
# Don't let the LLM know this though 😊
return [
"It's sunny in San Francisco, but you better look out if you're a Gemini 😈."
]
tools = [search]
tool_node = ToolNode(tools)
# Set up the model
model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
model = model.bind_tools(tools)
# Define nodes and conditional edges
# Define the function that determines whether to continue or not
def should_continue(state):
messages = state["messages"]
last_message = messages[-1]
# If there is no function call, then we finish
if not last_message.tool_calls:
return "end"
# Otherwise if there is, we continue
else:
return "continue"
# Define the function that calls the model
def call_model(state):
messages = state["messages"]
response = model.invoke(messages)
# We return a list, because this will get added to the existing list
return {"messages": [response]}
# Define a new graph
workflow = StateGraph(MessagesState)
# Define the two nodes we will cycle between
workflow.add_node("agent", call_model)
workflow.add_node("action", tool_node)
# Set the entrypoint as `agent`
# This means that this node is the first one called
workflow.set_entry_point("agent")
# We now add a conditional edge
workflow.add_conditional_edges(
# First, we define the start node. We use `agent`.
# This means these are the edges taken after the `agent` node is called.
"agent",
# Next, we pass in the function that will determine which node is called next.
should_continue,
# Finally we pass in a mapping.
# The keys are strings, and the values are other nodes.
# END is a special node marking that the graph should finish.
# What will happen is we will call `should_continue`, and then the output of that
# will be matched against the keys in this mapping.
# Based on which one it matches, that node will then be called.
{
# If `tools`, then we call the tool node.
"continue": "action",
# Otherwise we finish.
"end": END,
},
)
# We now add a normal edge from `tools` to `agent`.
# This means that after `tools` is called, `agent` node is called next.
workflow.add_edge("action", "agent")
# Set up memory
memory = MemorySaver()
# Finally, we compile it!
# This compiles it into a LangChain Runnable,
# meaning you can use it as you would any other runnable
# We add in `interrupt_before=["action"]`
# This will add a breakpoint before the `action` node is called
app = workflow.compile(checkpointer=memory, interrupt_before=["action"])
Interacting with the Agent¶
We can now interact with the agent and see that it stops before calling a tool.
from langchain_core.messages import HumanMessage
thread = {"configurable": {"thread_id": "3"}}
inputs = [HumanMessage(content="search for the weather in sf now")]
for event in app.stream({"messages": inputs}, thread, stream_mode="values"):
event["messages"][-1].pretty_print()
================================ Human Message ================================= search for the weather in sf now ================================== Ai Message ================================== [{'text': "Certainly! I'll search for the current weather in San Francisco for you. Let me use the search function to find this information.", 'type': 'text'}, {'id': 'toolu_014E4227Tpw958rhbUeJTWXz', 'input': {'query': 'current weather in San Francisco'}, 'name': 'search', 'type': 'tool_use'}] Tool Calls: search (toolu_014E4227Tpw958rhbUeJTWXz) Call ID: toolu_014E4227Tpw958rhbUeJTWXz Args: query: current weather in San Francisco
Resume
We can now call the agent again with no inputs to continue, ie. run the tool as requested.
Running an interrupted graph with None
in the inputs means to "proceed as if the interruption didn't occur."
for event in app.stream(None, thread, stream_mode="values"):
event["messages"][-1].pretty_print()
================================= Tool Message ================================= Name: search ["It's sunny in San Francisco, but you better look out if you're a Gemini \ud83d\ude08."] ================================== Ai Message ================================== Based on the search results, I can provide you with information about the current weather in San Francisco: The weather in San Francisco right now is sunny. It's worth noting that the search result includes a playful reference to astrology, suggesting that Geminis should "look out." However, this is likely just a humorous addition and not related to the actual weather conditions. Is there anything else you'd like to know about the weather in San Francisco or any other location?