snowflake.snowpark.DataFrameAIFunctions¶

class snowflake.snowpark.DataFrameAIFunctions(dataframe: snowflake.snowpark.DataFrame)[source]¶

Bases: object

Provides AI-powered functions for a DataFrame.

Methods

agg(task_description, input_column, *[, ...])	Aggregate a column of text data using a natural language task description.
classify(input_column, categories, *[, ...])	Classify text or images into specified categories using AI.
complete(prompt, input_columns, model, *[, ...])	Generate a response (completion) on each row using the specified language model.
count_tokens(model, prompt, *[, output_column])	Count the number of tokens in text for a specified language model.
embed(input_column, model, *[, output_column])	Generate embedding vectors from text or images.
extract(input_column, *[, response_format, ...])	Extract structured information from text or files using a response schema.
filter(predicate, input_columns, *)	Filter rows using AI-powered boolean classification.
parse_document(input_column, *[, output_column])	Extract content from a document (OCR or layout parsing) as JSON text.
sentiment(input_column[, categories, ...])	Extract sentiment analysis from text content.
similarity(input1, input2, *[, output_column])	Compute similarity scores between two columns using AI-powered embeddings.
split_text_markdown_header(text_to_split, ...)	Split Markdown-formatted text into structured chunks based on header levels.
split_text_recursive_character(...[, ...])	Split text into chunks using recursive character-based splitting.
summarize_agg(input_column, *[, output_column])	Summarize a column of text data using AI.
transcribe(input_column, *[, output_column])	Transcribe text from an audio file with optional timestamps and speaker labels.