evals.models.vertex

class GeminiModel(default_concurrency: int = 5, _verbose: bool = False, _rate_limiter: phoenix.evals.models.rate_limiters.RateLimiter = <factory>, project: Optional[str] = None, location: Optional[str] = None, credentials: Optional[ForwardRef('Credentials')] = None, model: str = 'gemini-pro', temperature: float = 0.0, max_tokens: int = 256, top_p: float = 1, top_k: int = 32, stop_sequences: List[str] = <factory>)

Bases: BaseModel

credentials: Credentials | None = None

default_concurrency: int = 5

property generation_config: Dict[str, Any]

location: str | None = None

The default location to use when making API calls. If not

Type:

location (str)

max_tokens: int = 256

The maximum number of tokens to generate in the completion.

model: str = 'gemini-pro'

The model name to use.

project: str | None = None

The default project to use when making API calls.

Type:

project (str)

reload_client() → None

stop_sequences: List[str]

If the model encounters a stop sequence, it stops generating further tokens.

temperature: float = 0.0

What sampling temperature to use.

top_k: int = 32

The cutoff where the model no longer selects the words

top_p: float = 1

Total probability mass of tokens to consider at each step.