streaming related code

[navaneethstabilix]

from langgraph.checkpoint.memory import MemorySaver
memory = MemorySaver()
react_graph_memory = builder.compile(checkpointer=memory)

how to add astream / stream for this code

[dosubot[bot]]

To add streaming to your code using MemorySaver and react_graph_memory, you can follow this example:

from langgraph.checkpoint.memory import MemorySaver
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.messages import HumanMessage

# Initialize memory saver
memory = MemorySaver()

# Create the language model and tools
model = ChatAnthropic(model_name="claude-3-sonnet-20240229")
search = TavilySearchResults(max_results=2)
tools = [search]

# Create the agent with memory
agent_executor = create_react_agent(model, tools, checkpointer=memory)

# Configuration with thread_id for memory
config = {"configurable": {"thread_id": "abc123"}}

# Stream messages with memory
for chunk in agent_executor.stream(
    {"messages": [HumanMessage(content="hi im bob! and i live in sf")]}, config
):
    print(chunk)
    print("----")

for chunk in agent_executor.stream(
    {"messages": [HumanMessage(content="whats the weather where I live?")]}, config
):
    print(chunk)
    print("----")

This code sets up an agent with memory using MemorySaver and streams messages while maintaining conversational context. The stream method processes messages iteratively, preserving the conversational state and context throughout the interaction ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}