Skip to content

Free Dev Day — June 25 — Virtual

Don’t just hear about AI — build it. Luminary talks and hands-on labs.

Claim my spot
Snowflake for Developers/Guides/Build a RAG-based Chatbot using Fivetran and Snowflake
Partner Solution

Build a RAG-based Chatbot using Fivetran and Snowflake

Fivetran Staff
Fork Repo

Overview

This solution architecture helps you understand how to build a retrieval augmented generation (RAG) application in Snowflake using structured PostgreSQL data. Some of the use cases are described below.

  • Leverage Fivetran to connect to and sync PostgreSQL data into Snowflake
  • Process structured data for RAG applications
  • Build a chatbot to interact with your data to plan California wine country visits

Solution Architecture: RAG-based California Wine Country Visit Assistant

Architecture Diagram
  • Fivetran reliably and securely moves PostgreSQL data into Snowflake
  • Structured data is processed and Cortex is used to create embeddings for downstream RAG application
  • Streamlit application provides a question/answer chat capability powered by Snowflake Cortex

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 It may be out of date with current Snowflake instances