CLI tool that reads a database schema and generates documentation using an LLM.
Project description
SchemaLens-Exillar — Quick Start Guide
CLI tool that connects to a database (PostgreSQL, MySQL, SQL Server, Snowflake, Databricks, or MongoDB), reads the schema, and uses an LLM to generate documentation automatically. No frontend. No manual input beyond a one-time setup wizard.
Requirements
- Python 3.11 or newer
- Internet access — to install the package, connect to your database, and call OpenAI
- Your database credentials (host, username, password, etc.)
- An OpenAI API key (platform.openai.com) — you're billed by OpenAI directly for usage
- SQL Server only: an ODBC Driver for SQL Server installed on your machine (not installed by pip — download here)
- Linux only, for diagram PNG export:
libcairo2system package (sudo apt install libcairo2)
Step-by-step
1. Create a virtual environment (recommended and required)
Don't install directly into your system Python — always use a virtual environment to avoid conflicts with other packages.
python -m venv venv
Activate it:
- Windows:
venv\Scripts\activate - Mac/Linux:
source venv/bin/activate
2. Install (pick the extra matching your database)
pip install SchemaLens-Exillar[postgres]
Options: [postgres], [mysql], [sqlserver], [snowflake], [databricks], [mongodb], or [all] for every driver.
3. Run
schemalens-exillar
4. Answer the wizard's questions
- Pick your database type (enter the number)
- Choose to paste a full connection string, or enter host/port/username/password one by one
- (Optional) Type specific schema names to limit scope (comma-separated, e.g. public,sales), or press Enter to include all schemas
- Enter your OpenAI API key — never saved, asked fresh every run
- Choose where to save the output (press Enter for current folder)
5. Wait for it to finish
You'll see a simple progress line per batch of tables being processed.
6. Open your files
Three files are created in the folder you chose:
er_diagram_<yourdatabase>.html— interactive diagram, open in any browserschema_documentation_<yourdatabase>.xlsx— Excel workbook with full column descriptionsSuggestion_Report_<yourdatabase>.docx— suggested keys/relationships for review
Run it again anytime — older files are never overwritten, each run adds a number + timestamp.
Each new session, reactivate the venv first (venv\Scripts\activate / source venv/bin/activate) before running schemalens-exillar again.
Note: nothing is ever saved to disk — no .env file, no saved password, no saved API key. You'll enter your credentials fresh every time you run it.
License
MIT — see LICENSE.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file schemalens_exillar-0.1.2.tar.gz.
File metadata
- Download URL: schemalens_exillar-0.1.2.tar.gz
- Upload date:
- Size: 1.1 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
620a4ff665a289e2c97ac81861f7daf6d22b9f487088a4d3cdc52f4e7ea7dad5
|
|
| MD5 |
4fa98b3d5814da752906d375fd89e8dc
|
|
| BLAKE2b-256 |
52ea48209c9ff2439e417bf626397022b79ecd00e76ecd6f7eb9bcd7d3a6eb10
|
File details
Details for the file schemalens_exillar-0.1.2-py3-none-any.whl.
File metadata
- Download URL: schemalens_exillar-0.1.2-py3-none-any.whl
- Upload date:
- Size: 1.0 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
92b4a84e5e379e2c5d2a818a2594196e5ade19a70bb49786357ff970cb9deec4
|
|
| MD5 |
274623680e6643e7f732ff6d10c454b9
|
|
| BLAKE2b-256 |
a9be076afe8ba5788243ab58f4d44a01056240c54e938ff782dee365892d2b23
|