Embedding LLM in SQL is simple!
Inspired by Snowflake’s AI-driven analytics and MotherDuck’s recent implementation of SQL + LLM (Introducing the prompt() function), I explored LLM-powered Business Insights using DuckDB, embedding AI directly into SQL workflows for real-time data intelligence.
Senthilnathan Karuppaiah
Introduction
Inspired by Snowflake’s AI-driven analytics and MotherDuck’s recent implementation of SQL + LLM ( Introducing the prompt() function), I explored LLM-powered Business Insights using DuckDB, embedding AI directly into SQL workflows for real-time data intelligence.
Use Case: Privacy Engineering – Detecting and Masking PII
The fully working code is available as a Jupyter Notebook, which can be accessed from my public GitHub Gist. Running the notebook will launch a Streamlit app with an interactive SQL editor.
📌 Note: To run LLM-powered SQL functions, you will need an OpenAI API key.
📌 GitHub Gist: streamlit-duckdb-sql-editor-with-embedded-llm.ipynb
GitHub Gist
streamlit-duckdb-sql-editor-with-embedded-llm.ipynb
Once you execute the code, you will see the Streamlit app with a built-in SQL editor:
