llm config_error ai_generated true

openai.BadRequestError: Invalid schema for response_format: 'properties' must be an object with string keys.

ID: llm/structured-output-schema-mismatch

Also available as: JSON · Markdown · 中文

90%Fix Rate

90%Confidence

1Evidence

2023-11-20First Seen

Version Compatibility

Version	Status	Introduced	Deprecated	Notes
openai>=1.0.0	active	—	—	—
openai>=1.12.0	active	—	—	—

Root Cause

The JSON schema provided in the response_format parameter is malformed, e.g., using integer keys or missing required fields like 'type'.

generic

中文

response_format参数中提供的JSON schema格式错误，例如使用整数键或缺少必需的字段如'type'。

Official Documentation

https://platform.openai.com/docs/guides/structured-outputs

Workarounds

95% success Use the Pydantic library to generate the schema automatically and validate it: from pydantic import BaseModel from openai import OpenAI class ResponseModel(BaseModel): name: str age: int client = OpenAI() schema = ResponseModel.model_json_schema() print(schema) # Check that 'properties' has string keys response = client.chat.completions.create( model='gpt-4o-mini', messages=[{'role': 'user', 'content': 'Extract info'}], response_format={ 'type': 'json_schema', 'json_schema': {'name': 'response', 'schema': schema} } )
```
Use the Pydantic library to generate the schema automatically and validate it:
from pydantic import BaseModel
from openai import OpenAI

class ResponseModel(BaseModel):
    name: str
    age: int

client = OpenAI()
schema = ResponseModel.model_json_schema()
print(schema)  # Check that 'properties' has string keys
response = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role': 'user', 'content': 'Extract info'}],
    response_format={
        'type': 'json_schema',
        'json_schema': {'name': 'response', 'schema': schema}
    }
)
```
90% success Manually ensure the schema has the correct structure: { 'type': 'object', 'properties': { 'name': {'type': 'string'}, 'age': {'type': 'integer'} }, 'required': ['name', 'age'] }
```
Manually ensure the schema has the correct structure:
{
    'type': 'object',
    'properties': {
        'name': {'type': 'string'},
        'age': {'type': 'integer'}
    },
    'required': ['name', 'age']
}
```

中文步骤

使用Pydantic库自动生成并验证schema：
from pydantic import BaseModel
from openai import OpenAI

class ResponseModel(BaseModel):
    name: str
    age: int

client = OpenAI()
schema = ResponseModel.model_json_schema()
print(schema)  # 检查'properties'是否有字符串键
response = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role': 'user', 'content': '提取信息'}],
    response_format={
        'type': 'json_schema',
        'json_schema': {'name': 'response', 'schema': schema}
    }
)

手动确保schema具有正确的结构：
{
    'type': 'object',
    'properties': {
        'name': {'type': 'string'},
        'age': {'type': 'integer'}
    },
    'required': ['name', 'age']
}

Dead Ends

Common approaches that don't work:

50% fail
OpenAI's schema validation is stricter than standard JSON; it requires specific keys like 'type': 'object' and 'properties' must be an object.
40% fail
Older models may not support the same schema features; the schema must comply with OpenAI's JSON Schema subset.