Overview
Concrete tool for constructing and serializing API response models provided by the Groq Python SDK's internal model layer.
Description
The BaseModel class extends Pydantic's BaseModel to provide a unified interface for API response deserialization that works across both Pydantic v1 and v2. It introduces to_dict() and to_json() convenience methods that default to API-friendly serialization (using alias names and excluding unset fields). The companion construct_type() function performs recursive, validation-free construction of nested model hierarchies from raw API response data, handling unions (including discriminated unions), generic types, dates, and primitive coercion.
Usage
All Groq API response types (ChatCompletion, Transcription, Model, ErrorObject, etc.) inherit from BaseModel. Users interact with BaseModel primarily through its to_dict() and to_json() serialization methods on response objects. The construct_type() function is used internally by the SDK to rapidly build response object graphs without expensive Pydantic validation.
Code Reference
Source Location
Signature
class BaseModel(pydantic.BaseModel):
def to_dict(
self,
*,
mode: Literal["json", "python"] = "python",
use_api_names: bool = True,
exclude_unset: bool = True,
exclude_defaults: bool = False,
exclude_none: bool = False,
warnings: bool = True,
) -> dict[str, object]: ...
def to_json(
self,
*,
indent: int | None = 2,
use_api_names: bool = True,
exclude_unset: bool = True,
exclude_defaults: bool = False,
exclude_none: bool = False,
warnings: bool = True,
) -> str: ...
@classmethod
def construct(
cls,
_fields_set: set[str] | None = None,
**values: object,
) -> "BaseModel": ...
def construct_type(
*,
value: object,
type_: object,
metadata: Optional[List[Any]] = None,
) -> object: ...
def validate_type(*, type_: type[_T], value: object) -> _T: ...
def build(
base_model_cls: Callable[P, _BaseModelT],
*args: P.args,
**kwargs: P.kwargs,
) -> _BaseModelT: ...
Import
from groq._models import BaseModel, GenericModel, construct_type, validate_type, build
I/O Contract
Inputs (BaseModel.to_dict)
| Name |
Type |
Required |
Description
|
| mode |
Literal["json", "python"] |
No |
Output mode; "json" produces JSON-safe types, "python" allows native types
|
| use_api_names |
bool |
No |
Whether to use API alias keys (default True)
|
| exclude_unset |
bool |
No |
Exclude fields not explicitly set (default True)
|
| exclude_defaults |
bool |
No |
Exclude fields at default values
|
| exclude_none |
bool |
No |
Exclude None-valued fields
|
Outputs (BaseModel.to_dict)
| Name |
Type |
Description
|
| return |
dict[str, object] |
Dictionary representation of the model
|
Inputs (construct_type)
| Name |
Type |
Required |
Description
|
| value |
object |
Yes |
Raw value from API response
|
| type_ |
object |
Yes |
Target type (may be annotated, generic, union)
|
| metadata |
Optional[List[Any]] |
No |
Annotation metadata for discriminated unions
|
Outputs (construct_type)
| Name |
Type |
Description
|
| return |
object |
Constructed instance of the target type
|
Usage Examples
Serializing a Response Object
from groq import Groq
client = Groq()
completion = client.chat.completions.create(
model="llama-3.3-70b-versatile",
messages=[{"role": "user", "content": "Hello"}],
)
# Convert response to dictionary with API field names
data = completion.to_dict()
# Convert to JSON string
json_str = completion.to_json(indent=2)
# Use Python field names instead of API names
python_dict = completion.to_dict(use_api_names=False)
# Include all fields, even those not set
full_dict = completion.to_dict(exclude_unset=False)
Related Pages
