OpenAIEmbedding

​

Parameters

Parameter	Type	Default	Description
api_key	Optional[str]	None	OpenAI API key
organization	Optional[str]	None	OpenAI organization ID
base_url	Optional[str]	None	Custom OpenAI API base URL
model_name	str	"text-embedding-3-small"	OpenAI embedding model
enable_rate_limiting	bool	True	Enable intelligent rate limiting
requests_per_minute	int	3000	Max requests per minute
tokens_per_minute	int	1000000	Max tokens per minute
parallel_requests	int	5	Number of parallel requests
request_timeout	float	60.0	Request timeout in seconds

​

Functions

​

__init__

Initialize the OpenAIEmbedding provider. Parameters:

• config (Optional[OpenAIEmbeddingConfig]): Configuration object
• **kwargs: Additional configuration options

​

_setup_client

Setup the OpenAI client with proper configuration.

​

supported_modes

Get supported embedding modes. Returns:

• List[EmbeddingMode]: List of supported embedding modes

​

pricing_info

Get current OpenAI embedding pricing. Returns:

• Dict[str, float]: Pricing information

​

get_model_info

Get information about the current OpenAI model. Returns:

• Dict[str, Any]: Model information

​

_check_rate_limits

Check and enforce rate limits. Parameters:

• estimated_tokens (int): Estimated token count

​

_estimate_tokens

Estimate token count for texts. Parameters:

• texts (List[str]): List of texts

Returns:

• int: Estimated token count

​

_embed_batch

Embed a batch of texts using OpenAI API. Parameters:

• texts (List[str]): List of text strings to embed
• mode (EmbeddingMode): Embedding mode (not used by OpenAI, but kept for compatibility)

Returns:

• List[List[float]]: List of embedding vectors

​

validate_connection

Validate OpenAI connection and model access. Returns:

• bool: True if connection is valid

​

get_usage_stats

Get detailed usage statistics for this session. Returns:

• Dict[str, Any]: Usage statistics

​

estimate_cost_detailed

Detailed cost estimation with breakdown. Parameters:

• num_texts (int): Number of texts
• avg_text_length (int): Average text length

Returns:

• Dict[str, Any]: Detailed cost estimation

​

_compare_model_cost

Compare cost with another model. Parameters:

• model_name (str): Model name to compare
• num_texts (int): Number of texts
• avg_text_length (int): Average text length

Returns:

• Dict[str, float]: Cost comparison

​

close

Clean up OpenAI client connections and resources.

​

create_openai_embedding

Quick factory function for OpenAI embeddings. Parameters:

• model_name (str): OpenAI model name
• api_key (Optional[str]): OpenAI API key (optional, uses env var if not provided)
• **kwargs: Additional configuration options

Returns:

• OpenAIEmbedding: Configured OpenAIEmbedding instance

​

create_ada_002_embedding

Create OpenAI Ada-002 embedding provider. Parameters:

• **kwargs: Additional configuration options

Returns:

• OpenAIEmbedding: Configured OpenAIEmbedding instance

​

create_3_small_embedding

Create OpenAI text-embedding-3-small provider. Parameters:

• **kwargs: Additional configuration options

Returns:

• OpenAIEmbedding: Configured OpenAIEmbedding instance

​

create_3_large_embedding

Create OpenAI text-embedding-3-large provider. Parameters:

• **kwargs: Additional configuration options

Returns:

• OpenAIEmbedding: Configured OpenAIEmbedding instance