How to stream state updates of your graph¶
LangGraph supports multiple streaming modes. The main ones are:
values
: This streaming mode streams back values of the graph. This is the full state of the graph after each node is called.updates
: This streaming mode streams back updates to the graph. This is the update to the state of the graph after each node is called.
This guide covers stream_mode="updates"
.
Setup¶
First, let's install the required package and set our API keys
import getpass
import os
def _set_env(var: str):
if not os.environ.get(var):
os.environ[var] = getpass.getpass(f"{var}: ")
_set_env("OPENAI_API_KEY")
Set up LangSmith for LangGraph development
Sign up for LangSmith to quickly spot issues and improve the performance of your LangGraph projects. LangSmith lets you use trace data to debug, test, and monitor your LLM apps built with LangGraph — read more about how to get started here.
Define the graph¶
We'll be using a simple ReAct agent for this guide.
from typing import Literal
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.runnables import ConfigurableField
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
@tool
def get_weather(city: Literal["nyc", "sf"]):
"""Use this to get weather information."""
if city == "nyc":
return "It might be cloudy in nyc"
elif city == "sf":
return "It's always sunny in sf"
else:
raise AssertionError("Unknown city")
tools = [get_weather]
model = ChatOpenAI(model_name="gpt-4o", temperature=0)
graph = create_react_agent(model, tools)
Stream updates¶
inputs = {"messages": [("human", "what's the weather in sf")]}
async for chunk in graph.astream(inputs, stream_mode="updates"):
for node, values in chunk.items():
print(f"Receiving update from node: '{node}'")
print(values)
print("\n\n")
Receiving update from node: 'agent'
{'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_kc6cvcEkTAUGRlSHrP4PK9fn', 'function': {'arguments': '{"city":"sf"}', 'name': 'get_weather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 57, 'total_tokens': 71}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-cd68b3a0-86c3-4afa-9649-1b962a0dd062-0', tool_calls=[{'name': 'get_weather', 'args': {'city': 'sf'}, 'id': 'call_kc6cvcEkTAUGRlSHrP4PK9fn'}], usage_metadata={'input_tokens': 57, 'output_tokens': 14, 'total_tokens': 71})]}
Receiving update from node: 'tools'
{'messages': [ToolMessage(content="It's always sunny in sf", name='get_weather', tool_call_id='call_kc6cvcEkTAUGRlSHrP4PK9fn')]}
Receiving update from node: 'agent'
{'messages': [AIMessage(content='The weather in San Francisco is currently sunny.', response_metadata={'token_usage': {'completion_tokens': 10, 'prompt_tokens': 84, 'total_tokens': 94}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3e7d703517', 'finish_reason': 'stop', 'logprobs': None}, id='run-009d83c4-b874-4acc-9494-20aba43132b9-0', usage_metadata={'input_tokens': 84, 'output_tokens': 10, 'total_tokens': 94})]}