LLMConfigsResource

LLMConfigsResource ¶

LLMConfigsResource(client: Client)

Bases: BaseResource

create ¶

create(name: str, llm_model_name: str, api_key: str, description: str = '', llm_base_url: str | None = None, api_version: str | None = None, max_connections: int = 10, max_retries: int | None = None, timeout: int | None = None, system_message: str | None = None, max_tokens: int | None = None, top_p: float | None = None, temperature: float | None = None, best_of: int | None = None, top_k: int | None = None, logprobs: bool | None = None, top_logprobs: int | None = None, reasoning_effort: str | None = None, inference_type: InferenceType = OPENAI) -> LLMConfig

Create a new LLM configuration.

Parameters:

Name	Type	Description	Default
`name`	`str`	Name for the LLM config.	required
`llm_model_name`	`str`	Name of the LLM model.	required
`api_key`	`str`	API key for the LLM service.	required
`description`	`str`	Optional description for the LLM config.	`''`
`llm_base_url`	`str \| None`	Optional base URL for the LLM service.	`None`
`api_version`	`str \| None`	Optional API version.	`None`
`max_connections`	`int`	Maximum number of concurrent connections to the LLM provider.	`10`
`max_retries`	`int \| None`	Optional maximum number of retries.	`None`
`timeout`	`int \| None`	Optional timeout in seconds.	`None`
`system_message`	`str \| None`	Optional system message for the LLM.	`None`
`max_tokens`	`int \| None`	Optional maximum tokens to generate.	`None`
`top_p`	`float \| None`	Optional nucleus sampling parameter.	`None`
`temperature`	`float \| None`	Optional temperature parameter.	`None`
`best_of`	`int \| None`	Optional number of completions to generate.	`None`
`top_k`	`int \| None`	Optional top-k sampling parameter.	`None`
`logprobs`	`bool \| None`	Optional flag to return log probabilities.	`None`
`top_logprobs`	`int \| None`	Optional number of top log probabilities to return.	`None`
`reasoning_effort`	`str \| None`	Optional reasoning effort parameter for o-series models.	`None`
`inference_type`	`InferenceType`	Type of Inference Provider to use.	`OPENAI`

Returns:

Type	Description
`LLMConfig`	The created LLM configuration.

Raises:

Type	Description
`HTTPStatusError`	If an LLM config with the same name already exists.

delete ¶

delete(llm_config: LLMConfig) -> None

Deletes an LLM configuration.

Parameters:

Name	Type	Description	Default
`llm_config`	`LLMConfig`	The LLM configuration to delete.	required

Raises:

Type	Description
`HTTPStatusError`	If the LLM config doesn't exist or belongs to a different project.

get ¶

get(name: str) -> LLMConfig

Get an LLM config by name.

Parameters:

Name	Type	Description	Default
`name`	`str`	Name of the LLM config.	required

Returns:

Type	Description
`LLMConfig`	The requested LLM config.

Raises:

Type	Description
`ValueError`	If no LLM config is found with the given name.

get_or_create ¶

get_or_create(name: str, llm_model_name: str, api_key: str, description: str = '', llm_base_url: str | None = None, api_version: str | None = None, max_connections: int = 10, max_retries: int | None = None, timeout: int | None = None, system_message: str | None = None, max_tokens: int | None = None, top_p: float | None = None, temperature: float | None = None, best_of: int | None = None, top_k: int | None = None, logprobs: bool | None = None, top_logprobs: int | None = None, reasoning_effort: str | None = None, inference_type: InferenceType = OPENAI) -> tuple[LLMConfig, bool]

Get an existing LLM config or create a new one.

The existence check is only based on the name parameter - if an LLM config with the given name exists, it will be returned regardless of the other parameters. If no config with that name exists, a new one will be created using all provided parameters.

Parameters:

Name	Type	Description	Default
`name`	`str`	Name for the LLM config.	required
`llm_model_name`	`str`	Name of the LLM model.	required
`api_key`	`str`	API key for the LLM service.	required
`description`	`str`	Optional description for the LLM config.	`''`
`llm_base_url`	`str \| None`	Optional base URL for the LLM service.	`None`
`api_version`	`str \| None`	Optional API version.	`None`
`max_connections`	`int`	Maximum number of concurrent connections to the LLM provider.	`10`
`max_retries`	`int \| None`	Optional maximum number of retries.	`None`
`timeout`	`int \| None`	Optional timeout in seconds.	`None`
`system_message`	`str \| None`	Optional system message for the LLM.	`None`
`max_tokens`	`int \| None`	Optional maximum tokens to generate.	`None`
`top_p`	`float \| None`	Optional nucleus sampling parameter.	`None`
`temperature`	`float \| None`	Optional temperature parameter.	`None`
`best_of`	`int \| None`	Optional number of completions to generate.	`None`
`top_k`	`int \| None`	Optional top-k sampling parameter.	`None`
`logprobs`	`bool \| None`	Optional flag to return log probabilities.	`None`
`top_logprobs`	`int \| None`	Optional number of top log probabilities to return.	`None`
`reasoning_effort`	`str \| None`	Optional reasoning effort parameter for o-series models.	`None`
`inference_type`	`InferenceType`	Type of Inference Provider to use.	`OPENAI`

Returns:

Type	Description
`tuple[LLMConfig, bool]`	tuple[LLMConfig, bool]: A tuple containing: - The LLM configuration - Boolean indicating if a new config was created (True) or existing one returned (False)