bigframes.ml.llm.Claude3TextGenerator#

class bigframes.ml.llm.Claude3TextGenerator(*, model_name: Literal['claude-3-sonnet', 'claude-3-haiku', 'claude-3-5-sonnet', 'claude-3-opus'] | None = None, session: Session | None = None, connection_name: str | None = None)[source]#

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

Note

This product or feature is subject to the Pre-GA Offerings Terms in the General Service Terms section of the Service Specific Terms(https://cloud.google.com/terms/service-terms#1). Pre-GA products and features are available as is and might have limited support. For more information, see the launch stage descriptions (https://cloud.google.com/products#product-launch-stages).

Note

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

Note

claude-3-sonnet model is deprecated. Use other models instead.

Parameters:

• model_name (str, Default to "claude-3-sonnet") The model for natural language tasks. Possible values are claude-3-sonnet, claude-3-haiku, claude-3-5-sonnet and claude-3-opus. claude-3-sonnet (deprecated) is Anthropics dependable combination of skills and speed. It is engineered to be dependable for scaled AI deployments across a variety of use cases. claude-3-haiku is Anthropics fastest, most compact vision and text model for near-instant responses to simple queries, meant for seamless AI experiences mimicking human interactions. claude-3-5-sonnet (deprecated) is Anthropics most powerful AI model and maintains the speed and cost of Claude 3 Sonnet, which is a mid-tier model. claude-3-opus (deprecated) is Anthropics second-most powerful AI model, with strong performance on highly complex tasks. https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude#available-claude-models If no setting is provided, claude-3-sonnet will be used by default and a warning will be issued.

• session (bigframes.Session or None) BQ session to create the model. If None, use the global default session.

• connection_name (str or None) Connection to connect with remote service. str of the format <PROJECT_NUMBER/PROJECT_ID>.<LOCATION>.<CONNECTION_ID>. If None, use default connection in session context. BigQuery DataFrame will try to create the connection and attach permission if the connection isnt fully set up.

predict(X: DataFrame | Series | DataFrame | Series, *, max_output_tokens: int = 128, top_k: int = 40, top_p: float = 0.95, max_retries: int = 0) → DataFrame[source]#

Predict the result from input DataFrame.

Parameters:

• X (bigframes.dataframe.DataFrame or bigframes.series.Series or pandas.core.frame.DataFrame or pandas.core.series.Series) Input DataFrame or Series, can contain one or more columns. If multiple columns are in the DataFrame, it must contain a prompt column for prediction. Prompts can include preamble, questions, suggestions, instructions, or examples.

• max_output_tokens (int, default 128) Maximum number of tokens that can be generated in the response. Specify a lower value for shorter responses and a higher value for longer responses. A token may be smaller than a word. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words. Default 128. Possible values are in the range [1, 4096].

• top_k (int, default 40) Top-k changes how the model selects tokens for output. A top-k of 1 means the selected token is the most probable among all tokens in the models vocabulary (also called greedy decoding), while a top-k of 3 means that the next token is selected from among the 3 most probable tokens (using temperature). For each token selection step, the top K tokens with the highest probabilities are sampled. Then tokens are further filtered based on topP with the final token selected using temperature sampling. Specify a lower value for less random responses and a higher value for more random responses. Default 40. Possible values [1, 40].

• top_p (float, default 0.95) Top-p changes how the model selects tokens for output. Tokens are selected from most K (see topK parameter) probable to least until the sum of their probabilities equals the top-p value. For example, if tokens A, B, and C have a probability of 0.3, 0.2, and 0.1 and the top-p value is 0.5, then the model will select either A or B as the next token (using temperature) and not consider C at all. Specify a lower value for less random responses and a higher value for more random responses. Default 0.95. Possible values [0.0, 1.0].

• max_retries (int, default 0) Max number of retries if the prediction for any rows failed. Each try needs to make progress (i.e. has successfully predicted rows) to continue the retry. Each retry will append newly succeeded rows. When the max retries are reached, the remaining rows (the ones without successful predictions) will be appended to the end of the result.

Returns:

DataFrame of shape (n_samples, n_input_columns + n_prediction_columns). Returns predicted values.

Return type:

bigframes.dataframe.DataFrame

to_gbq(model_name: str, replace: bool = False) → Claude3TextGenerator[source]#

Save the model to BigQuery.

Parameters:

• model_name (str) The name of the model.

• replace (bool, default False) Determine whether to replace if the model already exists. Default to False.

Returns:

Saved model.

Return type:

Claude3TextGenerator