langgraph structured output

[ankur995]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

part_1_tools = [
    consumer,
    ticketcreation,
]



part_1_assistant_runnable = primary_assistant_prompt | llm.bind_tools(part_1_tools)


# Build the state graph
builder = StateGraph(State)
builder.add_node("assistant", Assistant(part_1_assistant_runnable))
builder.add_node("tools", create_tool_node_with_fallback(part_1_tools))
builder.add_edge(START, "assistant")
builder.add_conditional_edges("assistant", tools_condition)
builder.add_edge("tools", "assistant")
builder.add_edge("assistant",END)


part_1_graph = builder.compile(checkpointer=memory)


def stream_graph_updates(user_input: str):
    for event in part_1_graph.stream({"messages": [("user", user_input)]}, {"configurable": {"thread_id": "1"}}):
        for value in event.values():
            print(value)
            last_message = value["messages"][-1]
            if hasattr(last_message, 'content'):
                print("Assistant:", last_message.content)
            else:
                print("Assistant: No valid content returned.")

Description

in this want i want llm response to be in json format where i required these field:
bot_response: final response from bot
intent: intent of user's query
sentiment:sentiment of user's query
language:language of user's query

System Info

not able to get structured response