Source
Cortex Search
Cortex Search enables low - latency, high - quality “fuzzy” search over your Snowflake data. It powers a broad array of search experiences for Snowflake users including Retrieval Augmented Generation (RAG) applications leveraging Large…
Cortex Playground
The Cortex Playground lets you compare text completions across the multiple large language models available in Cortex AI. You can test language model responses across prompts and model settings, and perform side - by - side comparisons…
Fine-tuning (Snowflake Cortex)
The Snowflake Cortex Fine - tuning function offers a way to customize large language models for your specific task. This topic describes how the feature works and how to get started with creating your own fine - tuned model. Overview Cortex…
Onboarding questions in Cortex Analyst
When your semantic model doesn’t include a Verified Query Repository (VQR), Cortex Analyst uses the underlying Large Language Models (LLMs) to generate up to three suggested questions. Note that these questions may not always be…
March 05, 2024 — Snowflake Cortex LLM Functions Release Notes –— Preview
This function accepts either a single prompt or a conversation with multiple prompts and responses. EXTRACT_ANSWER: Given a question and unstructured data, returns the answer to the question if it can be found in the data.
Sentiment extraction
AI_SENTIMENT uses a custom Snowflake large language model that delivers industry - leading overall sentiment and aspect - based sentiment accuracy. The following table provides information on how AI_SENTIMENT performs on Overall Sentiment and…
AI_COMPLETE (Single string)
Generates a response (completion) for a text prompt using a supported language model. Syntax The function contains two required arguments and four optional arguments. The function can be used with either positional or named argument…
FINETUNE (SNOWFLAKE.CORTEX)
This function lets you create and manage large language models customized for your specific task.
Snowflake AI and ML
ML Functions simplify the process of creating and using traditional machine learning models to detect patterns in your structured data. These powerful out - of - the - box analysis tools help time - strapped analysts, data engineers, and data…
Generate descriptions with Snowflake Cortex
The Cortex Powered Object Descriptions feature leverages Snowflake - hosted large language models (LLMs) to evaluate object metadata and, if desired, sample data to generate the description. The generated description, once saved, is…