# Issue with Structured Outputs Returning Invalid JSON Object **URL:** \ **Category:** API\ **Tags:** api, structured-output\ **Created:** [August 29, 2024, 3:19pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409 "2024-08-29T15:19:45Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![yonzbar](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yonzbar/32/8417_2.png) [@yonzbar](https://community.openai.com/u/yonzbar)\ **Post date:** [August 29, 2024, 3:19pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/1 "2024-08-29T15:19:45Z")
Hello everyone, I’m encountering an issue with the Structured Outputs feature when using the OpenAI API. The problem is that the API is returning an object that is not a valid JSON. Here is the object I’m receiving: MathReasoning(steps=[Step(explanation=‘We are given the equation 8x + 7 = -23. The goal is to solve for x, meaning we want to get x by itself on one side of the equation.’, output=‘Equation: 8x + 7 = -23’), Step(explanation=‘To start solving for x, we should isolate the term with x, which is 8x. We do this by eliminating the constant on the left side of the equation by subtracting 7 from both sides.’, output=‘Subtract 7 from both sides: 8x + 7 - 7 = -23 - 7’), Step(explanation=‘Subtracting 7 from both sides simplifies the equation to 8x = -30, because 7 - 7 is 0 and -23 - 7 is -30.’, output=‘Simplified equation: 8x = -30’), Step(explanation=‘To solve for x, we need to divide both sides of the equation by 8, the coefficient of x, to get x by itself.’, output=‘Divide both sides by 8: 8x/8 = -30/8’), Step(explanation=‘Dividing both sides by 8 simplifies the equation to x = -30/8. We can further simplify this by dividing the numerator and the denominator by their greatest common divisor, which is 2.’, output=‘Simplified: x = -15/4’), Step(explanation=“We’ve simplified the fraction -30/8 to -15/4 by dividing both the numerator and the denominator by 2.”, output=‘Final simplified form: x = -15/4’)], final\_answer=‘x = -15/4’) \*\*\*\* I’ve followed the code example provided in the official documentation. Here is the relevant code snippet:\*\*\*\*\*\* from openai import OpenAI from pydantic import BaseModel import os import json import requests class Step(BaseModel): explanation: str output: str class MathReasoning(BaseModel): steps: list[Step] final\_answer: str def call\_ai\_api(): print(‘!!! call\_ai\_api !!!’) ``` client = OpenAI() completion = client.beta.chat.completions.parse( model="gpt-4o-2024-08-06", messages=[ {"role": "system", "content": "You are a helpful math tutor. Guide the user through the solution step by step."}, {"role": "user", "content": "how can I solve 8x + 7 = -23"} ], response_format=MathReasoning, ) math_reasoning = completion.choices[0].message.parsed # Access the final answer directly from the MathReasoning object ai_message = math_reasoning #.final_answer return ai_message ``` def main(): ``` response = call_ai_api() print("\nAI Response:") print(response) print("\n" + "-"*50 + "\n") ``` if **name** == “ **main** ”: main() * * * The MathReasoning class is defined using Pydantic’s BaseModel to structure the response, and I’m using the OpenAI client to call the API. I’m not sure why the API is returning this object in an invalid JSON format, and I’d appreciate any guidance or suggestions on how to resolve this issue. Thank you in advance for your help! ---
**Author:** ![expertise.ai.chat](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/expertise.ai.chat/32/147254_2.png) [@expertise.ai.chat](https://community.openai.com/u/expertise.ai.chat)\ **Post date:** [August 29, 2024, 3:24pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/2 "2024-08-29T15:24:33Z")
Try calling `.dict()` on what you get back. ---
**Author:** ![yonzbar](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yonzbar/32/8417_2.png) [@yonzbar](https://community.openai.com/u/yonzbar)\ **Post date:** [August 29, 2024, 4:58pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/3 "2024-08-29T16:58:22Z")
Thanks for the suggestion! I tried calling `.dict()` on the object returned, and it did convert the object into a dictionary. However, the formatting used single quotes (`'`) for keys and string values instead of double quotes (`"`), which is required for valid JSON. This is causing issues when I try to work with the data as JSON. Is there a way to ensure that the output is properly formatted with double quotes? ---
**Author:** ![expertise.ai.chat](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/expertise.ai.chat/32/147254_2.png) [@expertise.ai.chat](https://community.openai.com/u/expertise.ai.chat)\ **Post date:** [August 29, 2024, 5:02pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/4 "2024-08-29T17:02:07Z")
Maybe you could try calling `json.loads()` on the output of `.dict()`. ---
**Author:** ![yonzbar](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yonzbar/32/8417_2.png) [@yonzbar](https://community.openai.com/u/yonzbar)\ **Post date:** [August 29, 2024, 5:15pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/5 "2024-08-29T17:15:12Z")
> [@expertise.ai.chat](#): > > `json.loads()` It seems it can’t handle the object: TypeError: loads() missing 1 required positional argument: ‘s’ ---
**Author:** ![expertise.ai.chat](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/expertise.ai.chat/32/147254_2.png) [@expertise.ai.chat](https://community.openai.com/u/expertise.ai.chat)\ **Post date:** [August 29, 2024, 5:17pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/6 "2024-08-29T17:17:19Z")
Is this what you did? ```auto foo = what_you_get_back_from_openai your_json_object = json.loads(foo.dict()) ``` ---
**Author:** ![yonzbar](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yonzbar/32/8417_2.png) [@yonzbar](https://community.openai.com/u/yonzbar)\ **Post date:** [August 29, 2024, 6:35pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/7 "2024-08-29T18:35:40Z")
> [@expertise.ai.chat](#): > > `json.loads(foo.dict())` First thing The method “dict” in class “BaseModel” is deprecated The `dict` method is deprecated; use `model_dump` instead.Pylance but: foo = what\_you\_get\_back\_from\_openai your\_json\_object = json.loads(foo.model\_dump()) brought me an error: TypeError: the JSON object must be str, bytes or bytearray, not dict Thanks so much for all the help! ---
**Author:** ![expertise.ai.chat](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/expertise.ai.chat/32/147254_2.png) [@expertise.ai.chat](https://community.openai.com/u/expertise.ai.chat)\ **Post date:** [August 29, 2024, 6:37pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/8 "2024-08-29T18:37:30Z")
Ah woops, looks like you want `json.dumps`, not `json.loads`. My bad. ---
**Author:** ![yonzbar](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yonzbar/32/8417_2.png) [@yonzbar](https://community.openai.com/u/yonzbar)\ **Post date:** [August 29, 2024, 7:01pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/9 "2024-08-29T19:01:38Z")
Still, the following code: math\_reasoning = completion.choices[0].message.parsed math\_reasoning = json.loads(math\_reasoning.model\_dump()) gives me the following error: TypeError: the JSON object must be str, bytes or bytearray, not dict And if in all this I try to use dict() instead of model\_dump() then I get an error: TypeError: the JSON object must be str, bytes or bytearray, not dict ---
**Author:** ![yonzbar](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yonzbar/32/8417_2.png) [@yonzbar](https://community.openai.com/u/yonzbar)\ **Post date:** [August 29, 2024, 7:52pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/10 "2024-08-29T19:52:48Z")
Thank you, now I understand what you meant. I take the object I receive, do a `model_dump()` on it, then `json.dumps()`, and now I have the JSON object ready. Thanks a lot! Although, it does seem like a pretty serious oversight by OpenAI. ---
**Author:** ![nicholishen](https://avatars.discourse-cdn.com/v4/letter/n/ecd19e/32.png) [@nicholishen](https://community.openai.com/u/nicholishen)\ **Post date:** [August 29, 2024, 8:12pm UTC](https://community.openai.com/t/issue-with-structured-outputs-returning-invalid-json-object/926409/11 "2024-08-29T20:12:40Z")
You are using a convenience method of the python SDK that returns a pydantic object, which is the documented behavior (adopted from the `instructor` package). If you don’t want to get a pydantic object then you can use the standard `client.chat.completions.chat` method to call the LLM.