SQLDatabase.from_uri Takes long time and we need to connect to database dynamically

[sanket20138339]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

db_connection = SQLDatabase.from_uri(connection_string)
 toolkit = SQLDatabaseToolkit(db=db_connection, llm=llm)

Description

We are using the LangChain SQL agent and it is working perfectly fine.
The only thing is SQLDatabase.from_uri it takes a long time as I understand it reads all schema and everything that is required for an agent.

We have a multi-tenant system that has multiple DBs and all DBs have the same structure.
but depending on the logged-in user I need to connect to the that tenant's DB but i use SQLDatabase.from_uri(connection_string) it will take a long time.

is there a way to change the connection string for SQLdatabase once the schema is read? so it will be faster

System Info

langchain==0.2.11
langchain-community==0.2.10
langchain-core==0.2.23
langchain-openai==0.1.17
langchain-text-splitters==0.2.2
langsmith==0.1.93

[IP050]

I don't fully understand your final question, but if you are looking to manage/store context of a db using SQLDatabase you could use:

db = SQLDatabase.from_uri(connection_string)
context = db.get_context() 
table_info = context['table_info'] 
table_names = ['table_names']

Where you could then pass those as prompt variables and set up a different connection with the same context, if that's what you are looking for.