The community members are discussing ways to speed up the load time for index creation in a SQL Database. The main points are:
- The slow part seems to be the SQLDatabase() constructor, and the community members suggest loading it once at startup to improve performance.
- Persisting the index to S3 does not seem to work as expected, as it does not store all the necessary information to reconstruct the index.
- The community members suggest using the NLSQLTableQueryEngine instead of the SQL index, as it is a better approach and the SQL index is slightly deprecated.
Any ideas on how to speed up the load time for index creation for SQL Database. It seems as though it takes a lot of time for it to do this at query, which is not optimal. Is it possible to do it before hand?
It seems very naive I'm doing this, I guess I should pre-index it and load it up on inference. Any ideas how much this will reduce inference time?
Is it supposed to be this way? It's asking me to define a SQL database again, not sure why. Looking at the files stored to s3, it seems not much info is persisted for it to reconstruct the index such as connection string, table name, etc.
Persisting a sql index doesn't actually do anything. Because all the data is in the sql database right? and you need the connection to the db to run anything. So yea it's intended to just be initialized when you need it
