Openai lm invoker

Defines a module to interact with OpenAI language models.

OpenAILMInvoker(model_name, api_key=None, base_url=OPENAI_DEFAULT_URL, model_kwargs=None, default_hyperparameters=None, tools=None, response_schema=None, output_analytics=False, retry_config=None, thinking=False, image_generation=False, data_stores=None, input_transformer=InputTransformerType.IDENTITY, output_transformer=OutputTransformerType.IDENTITY)

Bases: BaseLMInvoker

A language model invoker to interact with OpenAI language models.

This class provides support for OpenAI's Responses API schema, which is recommended by OpenAI as the preferred API to use whenever possible. Use this class unless you have a specific reason to use the Chat Completions API instead. The Chat Completions API schema is supported through the OpenAIChatCompletionsLMInvoker class.

Examples:

lm_invoker = OpenAILMInvoker(model_name="gpt-5-nano")
result = await lm_invoker.invoke("Hi there!")

Supported features

1. Basic invocation
2. Streaming output
3. Message roles
4. Multimodal input a. Text b. Document c. Image
5. Structured output
6. Tool calling
7. Native tools a. Code interpreter b. Data store c. Image generation d. MCP connector e. MCP server f. Web search
8. Thinking
9. Output analytics
10. Retry and timeout
11. Extra capabilities a. Input transformer b. Output transformer c. Batch invocation d. File management e. Data store management

For full documentation and examples, please refer to the LM Invoker tutorial: https://gdplabs.gitbook.io/sdk/gen-ai-sdk/tutorials/inference/lm-invoker

OpenAI compatible endpoints

This class can interact with endpoints compatible with OpenAI's Responses API schema (e.g. SGLang: https://github.com/sgl-project/sglang). To do this, simply set base_url to the endpoint URL. Supported features may vary between endpoints. Unsupported features will result in an error.

Attributes:

Name	Type	Description
model_id	str	The model ID of the language model.
model_provider	str	The provider of the language model.
model_name	str	The name of the language model.
client_kwargs	dict[str, Any]	The keyword arguments for the OpenAI client.
default_config	dict[str, Any]	Default config for invoking the model.
tools	list[Tool]	The list of tools provided to the model to enable tool calling.
response_schema	ResponseSchema | None	The schema of the response. If provided, the model will output a structured response as defined by the schema. Supports both Pydantic BaseModel and JSON schema dictionary.
output_analytics	bool	Whether to output the invocation analytics.
retry_config	RetryConfig	The retry configuration for the language model.
thinking	ThinkingConfig	The thinking configuration for the language model.
image_generation	bool	Whether to enable image generation.
data_stores	list[AttachmentStore]	The data stores to retrieve internal knowledge from.
input_transformer	InputTransformerType	The type of input transformer to use.
output_transformer	OutputTransformerType	The type of output transformer to use.

Initializes a new instance of the OpenAILMInvoker class.

Parameters:

Name	Type	Description	Default
model_name	str	The name of the OpenAI model.	required
api_key	str | None	The API key for authenticating with OpenAI. Defaults to None, in which case the OPENAI_API_KEY environment variable will be used. If the endpoint does not require an API key, a dummy value can be passed (e.g. "").	None
base_url	str	The base URL of a custom endpoint that is compatible with OpenAI's Responses API schema. Defaults to OpenAI's default URL.	OPENAI_DEFAULT_URL
model_kwargs	dict[str, Any] | None	Additional model parameters. Defaults to None.	None
default_hyperparameters	dict[str, Any] | None	Default hyperparameters for invoking the model. Defaults to None.	None
tools	list[LMTool] | None	Tools provided to the model to enable tool calling. Defaults to None, in which case an empty list is used.	None
response_schema	ResponseSchema | None	The schema of the response. If provided, the model will output a structured response as defined by the schema. Supports both Pydantic BaseModel and JSON schema dictionary. Defaults to None.	None
output_analytics	bool	Whether to output the invocation analytics. Defaults to False.	False
retry_config	RetryConfig | None	The retry configuration for the language model. Defaults to None, in which case a default config with no retry and 30.0 seconds timeout will be used.	None
thinking	bool | ThinkingConfig	A boolean or ThinkingConfig object to configure thinking. Defaults to False.	False
image_generation	bool	Whether to enable image generation. Defaults to False.	False
data_stores	list[AttachmentStore] | None	The data stores to retrieve internal knowledge from. Defaults to None, in which case no data stores will be used.	None
input_transformer	InputTransformerType	The type of input transformer to use. Defaults to InputTransformerType.IDENTITY, which returns the input without transformation.	IDENTITY
output_transformer	OutputTransformerType	The type of output transformer to use. Defaults to OutputTransformerType.IDENTITY, which returns the output without transformation.	IDENTITY

batch cached property

The batch operations for the language model.

Returns:

Name	Type	Description
OpenAIBatchOperations	OpenAIBatchOperations	The batch operations for the language model.

data_store cached property

The data store operations for the language model.

Returns:

Name	Type	Description
OpenAIDataStoreOperations	OpenAIDataStoreOperations	The data store operations for the language model.

file cached property

The file operations for the language model.

Returns:

Name	Type	Description
OpenAIFileOperations	OpenAIFileOperations	The file operations for the language model.

set_data_stores(data_stores)

Sets the data stores for the OpenAI language model.

This method sets the data stores for the OpenAI language model. Any existing data stores will be replaced.

Parameters:

Name	Type	Description	Default
data_stores	list[AttachmentStore]	The list of data stores to be used.	required