Skip to content

Convert natural language to SQL and chat with your data in SQL database

Notifications You must be signed in to change notification settings

mpraki/chat_with_database

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Chat with your database

img.png

Improvements:

  1. Use SystemMessage, HumanMessage, and AIMessage from langchain.schema instead of custom classes.
  2. To avoid dumb questions from users, add validators at each LLM call(or at-least at the vector search validator) to validate the input.
  3. Adjust the prompt to exclude the id columns(PK, FK) in the select query
  4. Once max revision is reached for the drafter, respond back to the user with Sorry message

About

Convert natural language to SQL and chat with your data in SQL database

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages