ChatDBT

Hi from Sweden! Rockie here, co-founder of Knock Data AB. We see DBT achieve a great step towards declarative data pipeline. And we see there are couple areas we could improve further to achieve better user experience. Here are the top 3. * Avoid context switch. Creating model, run it, checking data, plot all in the same environment. * Full GenAI integration. Using RAG to achieve both data security and intelligence with ChatDBT. * Allow stakeholder working directly on the app so that value can be delivered smoothly. In order to achieve the best end user experience, we break every technical assumption and design the app fully ground up. Here are couple things we designed. * DBT model parser with ground up using parser combinator. * Direct openai integration without any other libraries. * Vector database with pgvector directly * Ground up code editor and syntax highlighter. * Full frontend library * Automatic layout algorithm * Message with author directly inside the app Your feedback is highly appreciated; We're here to chat all day. Let's make data pipeline design enjoyable again, together!

In the real world, the gap between the data engineers and business requirements is usually the biggest hinder for fast data modelling and feature development. This is a really cool business driven tool that facilitates collaborations between business and data engineering and accelerates the development!

DBT projects get complex fast, it's great to have a tool to visualize and help understand the project.

Wow, there are so many fascinating features! I particularly enjoy the Visual Wholistic Overview feature. It's an essential tool for projects of all sizes, whether dealing with small or big data."

Having the ability to visualize a dbt project helps understanding the data pipeline, this tool is great for that.

So lovely can chat with author and can feel the author put so much love and passion on this product , love it!

Awesome tool to make it easier and faster to transform data within an organization. It helps streamline the process and make it more efficient, making it possible to handle larger amounts of data across different parts of the organization.