Output response in langraph

[navaneethstabilix]

for chunk in graph.stream({"messages": [("user", user_input)]}):

how to return the output response only in streaming to show in in an UI app .

[dosubot[bot]]

To return the output response only in streaming for display in a UI app using LangGraph, you can use the .stream method with stream_mode="messages". This allows you to stream output tokens as they are generated. Here's an example of how you can implement this:

config = {"configurable": {"thread_id": "abc789"}}
query = "Hi I'm Todd, please tell me a joke."
language = "English"

input_messages = [HumanMessage(query)]
for chunk, metadata in app.stream(
    {"messages": input_messages, "language": language},
    config,
    stream_mode="messages",
):
    if isinstance(chunk, AIMessage):  # Filter to just model responses
        print(chunk.content, end="|")

This code will stream each token of the model's response as it is generated, which can then be displayed in your UI app. The "messages" stream mode is appropriate for this use case as it emits LLM messages token-by-token, allowing for real-time updates in your UI ^[1][2][3].

To continue talking to Dosu, mention @dosu.

---

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