VolcEngineMaasBase#

class langchain_community.llms.volcengine_maas.VolcEngineMaasBase[source]#

Bases: BaseModel

Base class for VolcEngineMaas models.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param client: Any = None#
param connect_timeout: int | None = 60#

Timeout for connect to volc engine maas endpoint. Default is 60 seconds.

param endpoint: str | None = 'maas-api.ml-platform-cn-beijing.volces.com'#

Endpoint of the VolcEngineMaas LLM.

param model: str = 'skylark-lite-public'#

Model name. you could check this model details here https://www.volcengine.com/docs/82379/1133187 and you could choose other models by change this field

param model_kwargs: Dict[str, Any] [Optional]#

model special arguments, you could check detail on model page

param model_version: str | None = None#

Model version. Only used in moonshot large language model. you could check details here https://www.volcengine.com/docs/82379/1158281

param read_timeout: int | None = 60#

Timeout for read response from volc engine maas endpoint. Default is 60 seconds.

param region: str | None = 'Region'#

Region of the VolcEngineMaas LLM.

param streaming: bool = False#

Whether to stream the results.

param temperature: float | None = 0.95#

A non-negative float that tunes the degree of randomness in generation.

param top_p: float | None = 0.8#

Total probability mass of tokens to consider at each step.

param volc_engine_maas_ak: SecretStr | None = None#

access key for volc engine

param volc_engine_maas_sk: SecretStr | None = None#

secret key for volc engine

classmethod validate_environment(values: Dict) Dict[source]#
Parameters:

values (Dict)

Return type:

Dict