haive.core.models.llm.providers.fireworks¶

Fireworks AI Provider Module.

This module implements the Fireworks AI language model provider for the Haive framework, supporting fast inference for open-source models through Fireworks’ optimized infrastructure.

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

Examples

Basic usage:

from haive.core.models.llm.providers.fireworks import FireworksProvider

provider = FireworksProvider(
    model="accounts/fireworks/models/mixtral-8x7b-instruct",
    temperature=0.7,
    max_tokens=1000
)
llm = provider.instantiate()

With streaming:

provider = FireworksProvider(
    model="accounts/fireworks/models/llama-v2-70b-chat",
    temperature=0.1,
    stream=True,
    top_p=0.9
)

Classes¶

FireworksProvider

Fireworks AI language model provider configuration.

Module Contents¶

class haive.core.models.llm.providers.fireworks.FireworksProvider(/, **data)¶

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

Fireworks AI language model provider configuration.

This provider supports high-speed inference for open-source models through Fireworks’ optimized infrastructure, including Mixtral, Llama, and others.

Parameters:

data (Any)

provider¶

Always LLMProvider.FIREWORKS_AI

Type:

LLMProvider

model¶

The Fireworks model to use

Type:

str

temperature¶

Sampling temperature (0.0-2.0)

Type:

float

max_tokens¶

Maximum tokens in response

Type:

int

top_p¶

Nucleus sampling parameter

Type:

float

top_k¶

Top-k sampling parameter

Type:

int

stream¶

Enable streaming responses

Type:

bool

stop¶

Stop sequences for generation

Type:

list

Examples

Mixtral for reasoning:

provider = FireworksProvider(
    model="accounts/fireworks/models/mixtral-8x7b-instruct",
    temperature=0.3,
    max_tokens=2000
)

Llama 2 with streaming:

provider = FireworksProvider(
    model="accounts/fireworks/models/llama-v2-70b-chat",
    temperature=0.7,
    stream=True,
    top_p=0.9
)

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 Fireworks models.

Return type:

list[str]

max_tokens: int | None = None¶

Get maximum total tokens for this model.