haive.core.models.llm.providers.mistral

Mistral AI Provider Module.

This module implements the Mistral AI language model provider for the Haive framework, supporting Mistral’s family of high-performance open and commercial language models.

The provider handles API key management, model configuration, and safe imports of the langchain-mistralai package dependencies.

Examples

Basic usage:

from haive.core.models.llm.providers.mistral import MistralProvider

provider = MistralProvider(
    model="mistral-large-latest",
    temperature=0.7,
    max_tokens=1000
)
llm = provider.instantiate()

With function calling:

provider = MistralProvider(
    model="mistral-large-latest",
    temperature=0.1,
    max_tokens=2000
)

MistralProvider(*[, requests_per_second, ...])

Mistral AI language model provider configuration.

Classes

MistralProvider

Mistral AI language model provider configuration.

Module Contents

class haive.core.models.llm.providers.mistral.MistralProvider(/, **data)

Bases: haive.core.models.llm.providers.base.BaseLLMProvider

Mistral AI language model provider configuration.

This provider supports Mistral’s family of models including Mistral Large, Mistral Medium, Mistral Small, and the open Mixtral models.

Parameters:

• data (Any)

• requests_per_second (float | None)

• tokens_per_second (int | None)

• tokens_per_minute (int | None)

• max_retries (int)

• retry_delay (float)

• check_every_n_seconds (float | None)

• burst_size (int | None)

• provider (LLMProvider)

• model (str | None)

• name (str | None)

• api_key (SecretStr)

• cache_enabled (bool)

• cache_ttl (int | None)

• extra_params (dict[str, Any] | None)

• debug (bool)

• temperature (float | None)

• max_tokens (int | None)

• top_p (float | None)

• random_seed (int | None)

• safe_mode (bool)

provider

Always LLMProvider.MISTRALAI

Type:

LLMProvider

model

The Mistral model to use

Type:

str

temperature

Sampling temperature (0.0-1.0)

Type:

float

max_tokens

Maximum tokens in response

Type:

int

top_p

Nucleus sampling parameter

Type:

float

random_seed

Seed for reproducible generation

Type:

int

safe_mode

Enable content filtering

Type:

bool

Examples

Large model for complex tasks:

provider = MistralProvider(
    model="mistral-large-latest",
    temperature=0.7,
    max_tokens=2000
)

Small model for fast inference:

provider = MistralProvider(
    model="mistral-small-latest",
    temperature=0.1,
    max_tokens=500
)

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.

classmethod get_models()

Get available Mistral models.

Return type:

list[str]

max_tokens: int | None = None

Get maximum total tokens for this model.