Kueri development: Like Google Translate from natural language to SQL


Developers already know that on the one hand, we have SQL queries, and on the other hand, we have end users. But what will create a bridge between them? What will connect the end users, who do not know how to program but want to get information, to the databases?

This is where kueri.me enters the picture.

The user writes in natural language and the system converts it into SQL in real time

Kueri’s system enables developers to implant a unique search box within apps. The search box knows how to take questions from end users in natural language (Natural Language Processing – NLP) and translate them into SQL queries in real time. The app can run the queries through the database and display the results to the user. In addition, in order to make it even easier for the end user, it facilitates automatic completion during typing, with completions of words and smart suggestions according to the context of the search and database.

The system’s main challenge is the ability to do the conversion to SQL in real time. To do this, the system has to understand the database and connect the column headings, the various tables, and the data in the database – with sentence fragments in the end user’s question.

As soon as a developer uses the platform, he can define and connect an entire complex database that contains a large number of tables. The system can move freely between the tables and make the necessary connections. For example, if a question is asked like, “What is the sum of the salaries I paid to my five most outstanding salespeople?”, the system will be able to connect the salaries to a specific table and the sales to a different table, and then connect them, make the calculation, and give the user the sum.

Speaking with Geektime, Kueri Business Development Director Lee Laster explained that there are two differences between the company’s solution and others’ technologies: the interaction selected by the company – automatic completion – and secondly, the unique form of the analysis for the input obtained and disassembling the input into components.

When asked how they plan to make money, Laster told us, “Our product is currently offered in a freemium format, which is actually available for download by any user. The basic version – Kueri LITE – can connect to a single table, and in the enterprise version, which will be launched soon, connection with complex schemas is possible. A fixed monthly payment for a yearly license is charged for this version.”

Coming soon: A Chrome add-on for Google Analytics

Laster says that in the coming weeks, the company will also unveil a number of add-ons for Chrome based on the technology – for example, an add-on for Google Analytics users that will enable them to ask questions in free language, instead of dealing with all those menus and sub-menus. For example, a user can communicate with the system in free language by writing something like, “Show visitors from the U.S., and group them by operating software,” and get the data in real time.

Kueri.me – or its original name, SimpleQL – was founded in 2012 by CEO Yossi Shani and CTO Tal Cohen. In its present incarnation, however, it has been active since 2014. Since then, the company has raised $750,000 in seed funding and has taken part in the UpWest Labs accelerator program in California. The company currently has five employees.      


Please enter your comment!
Please enter your name here