Error while using OpenAI model with "parallel_tool_calls"

[qibinzhou-conveyor]

Checked other resources

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

Example Code

from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="GPT-4").with_structured_output(
    schema={
        ...
    },
)

model.invoke(prompt)

Error Message and Stack Trace (if applicable)

Error code: 400 - {'error': {'message': "Unknown parameter: 'parallel_tool_calls'.", 'type': 'invalid_request_error', 'param': 'parallel_tool_calls', 'code': 'unknown_parameter'}}

Description

I'm using OpenAI model with structured output. I'm experiencing flaky error with the error message above. Running with the same model and the same problem, sometimes it raises the error above, while sometimes it just goes through.

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 23.5.0: Wed May 1 20:17:33 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T6031
Python Version: 3.12.4 | packaged by Anaconda, Inc. | (main, Jun 18 2024, 10:07:17) [Clang 14.0.6 ]

Package Information

langchain_core: 0.2.29
langchain: 0.2.6
langchain_community: 0.2.6
langsmith: 0.1.98
langchain_openai: 0.1.13
langchain_text_splitters: 0.2.2

Optional packages not installed

langgraph
langserve

Other Dependencies

aiohttp: 3.10.1
async-timeout: Installed. No version info available.
dataclasses-json: 0.6.7
jsonpatch: 1.33
numpy: 1.26.4
openai: 1.40.1
orjson: 3.10.6
packaging: 24.1
pydantic: 2.8.2
PyYAML: 6.0.2
requests: 2.32.3
SQLAlchemy: 2.0.32
tenacity: 8.5.0
tiktoken: 0.7.0
typing-extensions: 4.12.2

[uglyrobot]

From OpenAI:
Structured Outputs is not compatible with parallel function calls. When a parallel function call is generated, it may not match supplied schemas. Set parallel_tool_calls: false to disable parallel function calling.

[qibinzhou-conveyor]

From OpenAI: Structured Outputs is not compatible with parallel function calls. When a parallel function call is generated, it may not match supplied schemas. Set parallel_tool_calls: false to disable parallel function calling.

I don't think that's the problem. Langchain set parallel_tool_calls as False. Also the err msg complaints about the existence of the field, not the value

[maximilianboth]

I currently have exactly the same problem. Is there a solution for this in the meantime? Thank you very much!

[thamid]

Any update on this? Thanks

[efriis]

Hey there! I can't reproduce with the following code

from langchain_openai import ChatOpenAI
from langchain_core.pydantic_v1 import BaseModel

class Person(BaseModel):
    """A Person"""
    name: str
    age: int

ChatOpenAI(model="gpt-4o").with_structured_output(schema=Person.schema()).invoke('john 1')

Could someone post their code that reproduces this?