connectors.openai_connector

OpenAI LLM Connector - OpenAI/GPT model integration

Classes

OpenAIConnector(api_key[, model, ...])	OpenAI LLM connector using Haystack
OpenAIConnectorFactory()	Factory for creating OpenAI connectors

class connectors.openai_connector.OpenAIConnector(api_key, model='gpt-3.5-turbo', api_base_url='https://api.openai.com/v1', timeout=60, streaming_callback=None, parameters=None)

Bases: BaseLLMConnector

OpenAI LLM connector using Haystack

__init__(api_key, model='gpt-3.5-turbo', api_base_url='https://api.openai.com/v1', timeout=60, streaming_callback=None, parameters=None)

Initialize OpenAI connector

Parameters:

• api_key (str) – OpenAI API key

• model (str) – Model name (e.g., gpt-3.5-turbo, gpt-4, gpt-4-turbo)

• api_base_url (str) – API base URL

• timeout (int) – Request timeout

• streaming_callback (Callable | None) – Optional streaming callback

• parameters (Dict[str, Any] | None) – Generation parameters (temperature, max_tokens, etc.)

generate(messages, generation_kwargs=None)

Generate response using OpenAI

class connectors.openai_connector.OpenAIConnectorFactory

Bases: object

Factory for creating OpenAI connectors

SUPPORTED_MODELS = ['gpt-3.5-turbo', 'gpt-3.5-turbo-16k', 'gpt-4', 'gpt-4-32k', 'gpt-4-turbo', 'gpt-4-turbo-preview', 'gpt-4o', 'gpt-4o-mini']

classmethod create(config, streaming_callback=None)

Create OpenAI connector from config

classmethod get_supported_models()

Get list of supported OpenAI models