haive.core.engine.embedding.providers.OpenAIEmbeddingConfig

OpenAI embedding configuration.

Classes

OpenAIEmbeddingConfig

Configuration for OpenAI embeddings.

Module Contents

class haive.core.engine.embedding.providers.OpenAIEmbeddingConfig.OpenAIEmbeddingConfig[source]

Bases: haive.core.engine.embedding.base.BaseEmbeddingConfig

Configuration for OpenAI embeddings.

This configuration provides access to OpenAI’s embedding models including the latest text-embedding-3-large and text-embedding-3-small models.

Examples

Basic usage:

config = OpenAIEmbeddingConfig(
    name="openai_embeddings",
    model="text-embedding-3-large",
    api_key="sk-..."
)

embeddings = config.instantiate()

With custom dimensions:

config = OpenAIEmbeddingConfig(
    name="openai_embeddings",
    model="text-embedding-3-large",
    dimensions=1536,
    api_key="sk-..."
)

Using environment variables:

# Set OPENAI_API_KEY environment variable
config = OpenAIEmbeddingConfig(
    name="openai_embeddings",
    model="text-embedding-3-large"
)
embedding_type

Always EmbeddingType.OPENAI

model

OpenAI model name (e.g., “text-embedding-3-large”)

api_key

OpenAI API key (auto-resolved from OPENAI_API_KEY env var)

dimensions

Output dimensions (optional, model-dependent)

max_retries

Maximum number of retries for API calls

request_timeout

Timeout for API requests in seconds

get_default_model()[source]

Get the default model for OpenAI embeddings.

Return type:

str

get_model_info()[source]

Get information about the configured model.

Return type:

dict

get_supported_models()[source]

Get list of supported OpenAI embedding models.

Return type:

list[str]

instantiate()[source]

Create an OpenAI embeddings instance.

Returns:

OpenAIEmbeddings instance configured with the provided parameters

Raises:
Return type:

Any

classmethod validate_dimensions(v, values)[source]

Validate dimensions based on model.

Return type:

Any

classmethod validate_model(v)[source]

Validate the OpenAI model name.

Return type:

Any