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