LangChain combined with grok-2-1212 using with_structured_output returns None

[moesmufti]

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

from langchain_xai import ChatXAI
from langchain_core.messages import HumanMessage

llm = ChatXAI(model="grok-2-1212", api_key=api_key).with_structured_output(Classification)
response = llm.invoke([HumanMessage(content='Hey how are you?')])

Description

• Using the new grok-2-1212 with the langchain-xai package, with structured output returns None. I tested not using any structured output and the model does return a response. You can put any kind of structured output (here some dummy "Classification" is used)

Note, using grok-beta does support the structured output.

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 24.1.0: Thu Oct 10 21:03:11 PDT 2024; root:xnu-11215.41.3~2/RELEASE_ARM64_T6020
Python Version: 3.12.6 (v3.12.6:a4a2d2b0d85, Sep 6 2024, 16:08:03) [Clang 13.0.0 (clang-1300.0.29.30)]

Package Information

langchain_core: 0.3.25
langsmith: 0.2.3
langchain_openai: 0.2.12
langchain_xai: 0.1.0

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.11.10
httpx: 0.28.1
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
openai: 1.57.4
orjson: 3.10.12
packaging: 24.2
pydantic: 2.10.3
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
tenacity: 9.0.0
tiktoken: 0.8.0
typing-extensions: 4.12.2