Class GeminiTextGenerator (1.30.0)

Stay organized with collections Save and categorize content based on your preferences.

The model for natural language tasks. Accepted values are "gemini-pro", "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" and "gemini-2.0-flash-exp". Default to "gemini-pro".

BQ session to create the model. If None, use the global default session.

Connection to connect with remote service. str of the format <PROJECT_NUMBER/PROJECT_ID>.

The number of steps to run when performing supervised tuning.

DataFrame of shape (n_samples, n_features). Training data.

Default True. If True, will return the parameters for this estimator and contained subobjects that are estimators.

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.

The temperature is used for sampling during the response generation, which occurs when topP and topK are applied. Temperature controls the degree of randomness in token selection. Lower temperatures are good for prompts that require a more deterministic and less open-ended or creative response, while higher temperatures can lead to more diverse or creative results. A temperature of 0 is deterministic: the highest probability response is always selected. Default 0.9. Possible values [0.0, 1.0].

Maximum number of tokens that can be generated in the response. A token is approximately four characters. 100 tokens correspond to roughly 60-80 words. Specify a lower value for shorter responses and a higher value for potentially longer responses. Default 8192. Possible values are in the range [1, 8192].

Top-K changes how the model selects tokens for output. A top-K of 1 means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a top-K of 3 means that the next token is selected from among the three most probable tokens by using temperature. For each token selection step, the top-K tokens with the highest probabilities are sampled. Then tokens are further filtered based on top-P 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 changes how the model selects tokens for output. Tokens are selected from the most (see top-K) to least probable 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 by using temperature and excludes C as a candidate. Specify a lower value for less random responses and a higher value for more random responses. Default 1.0. Possible values [0.0, 1.0].

Enables Grounding with Google Search for the Vertex AI model. When set to True, the model incorporates relevant information from Google Search results into its responses, enhancing their accuracy and factualness. This feature provides an additional column, ml_generate_text_grounding_result, in the response output, detailing the sources used for grounding. Note: Using this feature may impact billing costs. Refer to the pricing page for details: https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models The default is False.

Max number of retry rounds if any rows failed in the prediction. Each round need to make progress (has succeeded rows) to continue the next retry round. Each round will append newly succeeded rows. When the max retry rounds is reached, the remaining failed rows will be appended to the end of the result.

A BigQuery DataFrame as evaluation data, which contains only one column of input_text that contains the prompt text to use when evaluating the model.

A BigQuery DataFrame as evaluation labels, which contains only one column of output_text that you would expect to be returned by the model.

The type of the task for LLM model. Default to "text_generation". Possible values: "text_generation", "classification", "summarization", and "question_answering".

The name of the model.

Determine whether to replace if the model already exists. Default to False.