include_raw=True disable streaming

[underthesand]

Checked other resources

• [X] I added a very descriptive title to this issue.
• [X] I searched the LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.
• [X] I am sure that this is a bug in LangChain rather than my code.
• [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

Hello, there is no way to retrieve the tokens used (usage) with Azure when using streaming and structured_output.

structured_llm = llm.with_structured_output(Joke, include_raw=True)

for chunk in structured_llm.stream("Tell me a joke about cats")
    print(chunk)

https://python.langchain.com/docs/how_to/structured_output/

Error Message and Stack Trace (if applicable)

No response

Description

This code disables streaming. We have to wait for the complete generation to get a response.

Expected behavior: We should be able to use streaming and retrieve the usage metadata at the end.

System Info

System Information

OS: Linux OS Version: #47~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Oct 2 16:16:55 UTC 2 Python Version: 3.11.10 | packaged by conda-forge | (main, Sep 22 2024, 14:10:38) [GCC 13.3.0]

Package Information

langchain_core: 0.3.12 langchain: 0.3.3 langsmith: 0.1.128 langchain_openai: 0.2.2 langchain_text_splitters: 0.3.0

Optional packages not installed

langgraph langserve

Other Dependencies

aiohttp: 3.9.5 async-timeout: Installed. No version info available. httpx: 0.27.0 jsonpatch: 1.33 numpy: 1.26.4 openai: 1.52.0 orjson: 3.10.5 packaging: 24.1 pydantic: 2.7.4 PyYAML: 6.0.1 requests: 2.32.3 SQLAlchemy: 2.0.35 tenacity: 8.5.0 tiktoken: 0.7.0 typing-extensions: 4.12.2

[eyurtsev]

We don't have a chunk for this kind of 2-tuple right now. What's your use case?

[underthesand]

hello, get tokens used (usage) with Azure when using streaming and structured_output