Skip to content

Mphasis-ML-Marketplace/Text-to-SQL-using-LLM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Text-to-SQL-using-LLM

Product Overview

The solution generates complex SQL queries using bedrock models given a question prompt. The solution also validates the generated queries by testing them with sample data to ensure a smooth run without any errors. The solution requires only two input files containing questions in the English language and a data schema with metadata in JSON format. The output file contains the SQL queries perfectly ready to run. If the asked question is to complex the suggested changes will also get generated along with the query.

Product Highlight

  • The solution can be useful to analyze the multi-tabular data without giving the actual data. It generates complex SQL queries given appropriate prompts on one table schema at a time and up to 4 questions in a single inference. It also validates the queries for a smooth run and also returns the error or warning if any.
  • It can be used for data analysis tasks, to extract information from tabular data, and does not require any expertise in SQL. The users required only the AWS credentials of an account that has a bedrock anthropic-claude-instant-v1 model subscription.
  • Mphasis DeepInsights is a cloud-based cognitive computing platform that offers data extraction & predictive analytics capabilities. Need customized Machine Learning and Deep Learning solutions? Get in touch!

Amazon Marketplace Link

The product can be found here

About

This solution generates SQL query given a table schema and associated meta data and validate it through a dry run

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published