amoffat/HeimdaLLM

Constrain LLM output

39
/ 100
Emerging

When your team uses AI to generate SQL queries from natural language, HeimdaLLM acts as a security guard, making sure the generated SQL code is safe before it runs. It takes an AI-generated SQL query and analyzes it to ensure it only accesses authorized data, tables, and functions. This tool is for data engineers, database administrators, or anyone responsible for database security when integrating Large Language Models.

113 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to ensure that AI-generated SQL queries are secure, restricted to specific data, and won't accidentally expose sensitive information or damage your production databases.

Not ideal if you are looking for a tool to generate SQL queries from natural language, as this project focuses on validating already generated queries rather than creating them.

database-security SQL-validation data-governance AI-safety data-operations
Stale 6m
Maintenance 0 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 5 / 25

How are scores calculated?

Stars

113

Forks

3

Language

Python

License

AGPL-3.0

Last pushed

Jul 16, 2024

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/amoffat/HeimdaLLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.