0
0
DBT AI
This application provides AI generated recommendations on how to improve your dbt models.
Features
Scans all dbt models and generates a report containing recommendations for each model
Lists dbt models that are missing associated metadata e.g. in a schema.yml file or equivalent
Installation
You can install the application here
pip install dbt-ai == 0 .0.10a0
WARNING: This is an early phase application that may still contain bugs
Prerequisites
In order to benefit from AI recommendations, you need your own OpenAI API Key with the initial version of this application Once you sign up to OpenAI you can create an API key. Trial version gives you a certain amount of credits allowing you to make many API calls Usage beyond the trial credits require billing details. API usage pricing provides more info
Ideally you already have dbt project to test this out on
Python 3.10 or greater is required
Usage
Set up your OpenAI API key as an environment variable:
export OPENAI_API_KEY = “your_openai_api_key”
Run the application passing in the path to your dbt project:
dbt-ai path/to/dbt/project
Please allow some time for the AI model to process your dbt models. The application will process all dbt model files in your project and generate an HTML report with suggestions for each model. The report will be saved as dbt_model_suggestions.html within the dbt project directory. Upon generation of the report, it will be opened in a new browser tab.
Generated Report
This shows an example of a report generated from a DBT project containing 3 models
Contributing
We welcome contributions to the project! Please feel free to open issues or submit pull requests with your improvements and suggestions.
See CONTRIBUTING.md to get started and develop in this repo.
GPT’s reaction to this article:
As an AI language model, I cannot have an opinion on the article, but I can provide you with some information. This article describes a tool called DBT AI, which provides AI-generated recommendations on how to improve your DBT models. DBT is a popular open-source tool that helps data teams transform and test data in their data warehouse. DBT AI scans all DBT models and generates a report containing recommendations for each model. It also lists DBT models that are missing associated metadata. To use DBT AI, you need your own OpenAI API key, and Python 3.10 or greater is required. The application is still in the early phase and may contain bugs.
