
New developers joining a team often inherit databases with dozens or hundreds of tables and no documentation. Understanding the schema, key relationships, and how to write useful queries can take days or weeks of painful reverse-engineering. Rosetta solves this by automating the entire onboarding experience. You connect it to a SQL Server or SQLite database, and within minutes it produces a complete, interactive documentation hub tailored to that database. Under the hood, Rosetta uses pyodbc and sqlite3 to inspect the live schema — extracting tables, columns, data types, foreign key relationships, and row counts directly from the database system catalog. That metadata is then sent to the Groq API running Llama 3.1 8B Instant, which generates a plain-language database overview, one-sentence descriptions for every table, a ranked list of the five most important tables to learn first, and a set of starter SQL queries a new developer would actually need. The result is a 7-page Streamlit application with: a natural language overview of what the database is and what it stores, an interactive force-directed schema map showing every table and foreign key relationship color-coded by schema, a "Spotlight" guide ranking which five tables matter most and why, a library of AI-generated queries you can run live and download as CSV, a searchable and filterable table glossary with full column details, and a one-click PDF export of the complete onboarding document. A built-in SQLite demo database with 37 tables is included so anyone can try the full experience without a database connection. Built entirely in Python using Streamlit, pyodbc, pandas, streamlit-agraph, reportlab, and the Groq API — Rosetta deploys for free on Streamlit Cloud.
17 May 2026