isra36 - SQL helper for developers
Text to working SQL query. For those who forget SQL syntax
3 followers
Text to working SQL query. For those who forget SQL syntax
3 followers
Text to working SQL query. For developers who know logic but forget SQL query syntax. How it differs from GPT: It double-checks query in isolated sandbox, creates tables, mock data and gives working SQL query and details of the process. Currenlty, the main goal is to generate code that is free from SQL syntax errors. As you will see below in example (image), complex task will require 2,3 auto-error fixing itterations.
What isra36 does?
It generates an SQL query based on your prompt. Then it creates an isolated sandbox with the necessary tables and mock data according to your prompt, and executes the query. If the generated query doesn't work, it will try to fix it in a self debugging iteration loop (we have a limit of 4 iterations).
When using LLMs (GPT, Claude, etc.) you can generate a very large SQL query, but it can take a lot of time to debug and understand what is wrong. Or you can generate queries using an LLM's step-by-step process, but in that case you always need to double-check whether the newly generated query works or not in some environment. isra36 automates these steps.
What isra36 does not do?
It doesn't connect to your database. You get only the working SQL query, details of the process and the state of isolated sandbox environment, so you will be sure that the query is working, and doesn't need to double-check. Benefits: privacy. If you think that some features (connect to database, optimize query, e.t.c) can be helpful for developers, please ask in Feedback section.
However, we have plans to give an ability to upload your schema without any data. In this case isra36 will decide which tables are required for this task, and will generate sandbox with neccessary tables and mock data. So you can just copy and paste query. Please visit our Roadmap page for more details and help us to shape the future of this project. Currently we are validating this idea.
It doesn't optimize your query. Hope yet :)
Real usage example:
At work, I was tasked with creating a custom report for a client. The task required getting the number of EntityA (let's say it was Products) by it's width and height, grouped by nested and one to many related categories.
And here is the prompt I used for isra36:
Get data by Country of origin of products grouped by category and grouped by products width and height with their count. Width and height are in settings table, product info in products table, categories in categories table. 1 product can have multiple categories. Output should be like: columns: Country | Categories | values: Uzbekistan | {"Category1": {"135x70": 3, "120x65": 2}, "Category2" : {"135x70": 1, "120x65": 1} |
See the result of this prompt in attached 3rd long thin image :) in media's
Swytchcode
Looking for your product to be live