haive.core.models.llm.providers.azure¶

Azure OpenAI Provider Module.

This module implements the Azure OpenAI language model provider for the Haive framework, supporting GPT models deployed on Microsoft Azure with enhanced security and compliance.

The provider handles Azure-specific authentication, endpoint configuration, and model deployment access through the langchain-openai package dependencies.

Examples

Basic usage:

from haive.core.models.llm.providers.azure import AzureOpenAIProvider

provider = AzureOpenAIProvider(
    deployment_name="gpt-4-deployment",
    azure_endpoint="https://myresource.openai.azure.com/",
    api_version="2024-02-15-preview",
    temperature=0.7
)
llm = provider.instantiate()

With Azure AD authentication:

provider = AzureOpenAIProvider(
    deployment_name="gpt-35-turbo",
    azure_endpoint="https://myresource.openai.azure.com/",
    use_azure_ad=True
)

AzureOpenAIProvider(*[, ...])

Azure OpenAI language model provider configuration.

Classes¶

AzureOpenAIProvider

Azure OpenAI language model provider configuration.

Module Contents¶

class haive.core.models.llm.providers.azure.AzureOpenAIProvider(/, **data)[source]¶

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

Azure OpenAI language model provider configuration.

This provider supports all OpenAI models deployed on Microsoft Azure, including GPT-4, GPT-3.5-turbo, and others with enterprise-grade security.

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)
deployment_name (str)
azure_endpoint (str)
api_version (str)
use_azure_ad (bool)
temperature (float | None)
max_tokens (int | None)
top_p (float | None)
frequency_penalty (float | None)
presence_penalty (float | None)

provider¶

Always LLMProvider.AZURE

Type:: LLMProvider

deployment_name¶

Azure deployment name for the model

Type:: str

azure_endpoint¶

Azure OpenAI resource endpoint URL

Type:: str

api_version¶

Azure OpenAI API version

Type:: str

use_azure_ad¶

Whether to use Azure AD authentication

Type:: bool

temperature¶

Sampling temperature (0.0-2.0)

Type:: float

max_tokens¶

Maximum tokens in response

Type:: int

top_p¶

Nucleus sampling parameter

Type:: float

frequency_penalty¶

Frequency penalty parameter

Type:: float

presence_penalty¶

Presence penalty parameter

Type:: float

Examples

Standard deployment:

provider = AzureOpenAIProvider(
    deployment_name="gpt-4",
    azure_endpoint="https://myresource.openai.azure.com/",
    temperature=0.7,
    max_tokens=1000
)

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 validate_endpoint(v)[source]¶

Validate Azure endpoint format.

Parameters:: v (str)
Return type:: str

max_tokens: int | None = None¶: Get maximum total tokens for this model.