Streaming with Agent Executor

[sumanth2002629]

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

agent_executor = create_react_agent(llm, tools)

chunks = []
for chunk in agent_executor.stream({"messages":"what is today's date?"}):
    chunks.append(chunk)
    print(chunk)

# I need the output to be a stream of tokens of the final output and not the steps to reach final output. How to proceed?

Description

We are using the agentExecutor and agent.stream() is streaming the sequence of steps(eg: AI_msg->Tool_msg->AI_msg) needed to get the final output.

But we need the tokens of the final output to be streamed just like mode.stream().. any way how to do it using agentExecutor?

System Info

System Information

OS: Windows
OS Version: 10.0.22631
Python Version: 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)]

Package Information

langchain_core: 0.3.9
langchain: 0.3.2
langsmith: 0.1.132
langchain_openai: 0.2.2
langchain_text_splitters: 0.3.0
langgraph: 0.2.34

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.10.9
async-timeout: Installed. No version info available.
httpx: 0.27.2
jsonpatch: 1.33
langgraph-checkpoint: 2.0.1
numpy: 1.26.4
openai: 1.51.2
orjson: 3.10.7
packaging: 24.1
pydantic: 2.9.2
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.35
tenacity: 8.5.0
tiktoken: 0.8.0
typing-extensions: 4.12.2