Module llm (2.29.0)

LLM models.

Classes

Claude3TextGenerator

Claude3TextGenerator(     *,     model_name: typing.Optional[         typing.Literal[             "claude-3-sonnet", "claude-3-haiku", "claude-3-5-sonnet", "claude-3-opus"         ]     ] = None,     session: typing.Optional[bigframes.session.Session] = None,     connection_name: typing.Optional[str] = None )

Claude3 text generator LLM model.

Go to Google Cloud Console -> Vertex AI -> Model Garden page to enable the models before use. Must have the Consumer Procurement Entitlement Manager Identity and Access Management (IAM) role to enable the models. https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-partner-models#grant-permissions

The models only available in specific regions. Check https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude#regions for details.

GeminiTextGenerator

GeminiTextGenerator(     *,     model_name: typing.Optional[         typing.Literal[             "gemini-1.5-pro-preview-0514",             "gemini-1.5-flash-preview-0514",             "gemini-1.5-pro-001",             "gemini-1.5-pro-002",             "gemini-1.5-flash-001",             "gemini-1.5-flash-002",             "gemini-2.0-flash-exp",             "gemini-2.0-flash-001",             "gemini-2.0-flash-lite-001",         ]     ] = None,     session: typing.Optional[bigframes.session.Session] = None,     connection_name: typing.Optional[str] = None,     max_iterations: int = 300 )

Gemini text generator LLM model.

MultimodalEmbeddingGenerator

MultimodalEmbeddingGenerator(     *,     model_name: typing.Optional[typing.Literal["multimodalembedding@001"]] = None,     session: typing.Optional[bigframes.session.Session] = None,     connection_name: typing.Optional[str] = None )

Multimodal embedding generator LLM model.

TextEmbeddingGenerator

TextEmbeddingGenerator(     *,     model_name: typing.Optional[         typing.Literal[             "text-embedding-005",             "text-embedding-004",             "text-multilingual-embedding-002",         ]     ] = None,     session: typing.Optional[bigframes.session.Session] = None,     connection_name: typing.Optional[str] = None )

Text embedding generator LLM model.