Skip to content

Summit 26 from June 1-4 in San Francisco

Lead your organization in the era of agents and enterprise intelligence.

register now
Snowflake for DevelopersGuidesFine tuning LLMs using Snowpark Container Services and Amazon Bedrock

Fine tuning LLMs using Snowpark Container Services and Amazon Bedrock

AWS Staff
fork repo

Overview

This solution architecture shows how to build an AI application that uses Amazon Bedrock and Snowflake to create personalized marketing messages to customers.

  • Set up environments in both Snowflake and AWS.
  • Create a function that leverages Snowpark External Access to make a call to Amazon Bedrock.
  • Create a Streamlit app that leverages the above function to generate responses using data from Snowflake and prompts.

Solution Architecture: Fine tuning LLMs using Snowpark Container Services and Amazon Bedrock

Architecture Diagram
  • The user interacts with the Streamlit app and provides a prompt and/or parameters.
  • The Streamlit app receives those prompts and accesses relevant data from Snowflake.
  • The app passes the prompts from the user and the Snowflake data to a Bedrock model endpoint using Snowpark External Access to generate a response.
  • The Streamlit app materializes the response back to the user.

Get Started

Updated 2026-04-29

This content is provided as is, and is not maintained on an ongoing basis. It may be out of date with current Snowflake instances