mistral_common.protocol.instruct.request

ChatCompletionRequest(**data)

Bases: BaseCompletionRequest, Generic[ChatMessageType]

Request for a chat completion.

Attributes:

Name	Type	Description
model	Optional[str]	The model to use for the chat completion.
messages	List[ChatMessageType]	The messages to use for the chat completion.
response_format	ResponseFormat	The format of the response.
tools	Optional[List[Tool]]	The tools to use for the chat completion.
tool_choice	ToolChoice	The tool choice to use for the chat completion.
truncate_for_context_length	bool	Whether to truncate the messages for the context length.

Examples:

>>> from mistral_common.protocol.instruct.messages import UserMessage, AssistantMessage
>>> from mistral_common.protocol.instruct.tool_calls import ToolTypes, Function
>>> request = ChatCompletionRequest(
...     messages=[
...         UserMessage(content="Hello!"),
...         AssistantMessage(content="Hi! How can I help you?"),
...     ],
...     response_format=ResponseFormat(type=ResponseFormats.text),
...     tools=[Tool(type=ToolTypes.function, function=Function(name="get_weather", parameters={}))],
...     tool_choice=ToolChoice.auto,
...     truncate_for_context_length=True,
... )

Source code in .venv/lib/python3.13/site-packages/pydantic/main.py

def __init__(self, /, **data: Any) -> None:
    """Create a new model by parsing and validating input data from keyword arguments.

    Raises [`ValidationError`][pydantic_core.ValidationError] if the input data cannot be
    validated to form a valid model.

    `self` is explicitly positional-only to allow `self` as a field name.
    """
    # `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks
    __tracebackhide__ = True
    validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
    if self is not validated_self:
        warnings.warn(
            'A custom validator is returning a value other than `self`.\n'
            "Returning anything other than `self` from a top level model validator isn't supported when validating via `__init__`.\n"
            'See the `model_validator` docs (https://docs.pydantic.dev/latest/concepts/validators/#model-validators) for more details.',
            stacklevel=2,
        )

ResponseFormat(**data)

Bases: MistralBase

The format of the response.

Attributes:

Name	Type	Description
type	ResponseFormats	The type of the response.

Examples:

>>> response_format = ResponseFormat(type=ResponseFormats.text)

Source code in .venv/lib/python3.13/site-packages/pydantic/main.py

def __init__(self, /, **data: Any) -> None:
    """Create a new model by parsing and validating input data from keyword arguments.

    Raises [`ValidationError`][pydantic_core.ValidationError] if the input data cannot be
    validated to form a valid model.

    `self` is explicitly positional-only to allow `self` as a field name.
    """
    # `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks
    __tracebackhide__ = True
    validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
    if self is not validated_self:
        warnings.warn(
            'A custom validator is returning a value other than `self`.\n'
            "Returning anything other than `self` from a top level model validator isn't supported when validating via `__init__`.\n"
            'See the `model_validator` docs (https://docs.pydantic.dev/latest/concepts/validators/#model-validators) for more details.',
            stacklevel=2,
        )

ResponseFormats

Bases: str, Enum

Enum of the different formats of an instruct response.

Attributes:

Name	Type	Description
text		The response is a plain text.
json		The response is a JSON object.

Examples:

>>> response_format = ResponseFormats.text