port undefined error in SQLDatabase.from_databricks (langchain.sql_database)

[Octavian1]

The following assignment:

from langchain.sql_database import SQLDatabase

dbase = SQLDatabase.from_databricks(
catalog=catalog, 
schema=db,
host=host, 
api_token=token,
)

fails with 

ValueError: invalid literal for int() with base 10: ''

because of

cls._assert_port(port),

in /lib/python3.10/site-packages/sqlalchemy/engine/url.py:211, in URL.create(cls, drivername, username, password, host, port, database, query)
as shown in the error trace.

Couldn't find any information regarding this (for instance, in the example given in: https://docs.gcp.databricks.com/en/large-language-models/langchain.html)

The token and host are OK. Also the catalog and schema have correct values.

Using langchain==0.1.5.

[Kaniz]

Hi @Octavian1, Ensure that the port parameter you’re passing to SQLDatabase.from_databricks is a valid integer. If it’s empty or contains non-numeric characters, that could be the root cause.

• In a Stack Overflow post, someone faced a similar issue while connecting SQLAlchemy (SQLDatabaseChain from langchain) to SingleStoreDB. They provided a workaround using a custom connection URL. 
• Here’s an example snippet:

  from sqlalchemy import create_engine
  engine = create_engine(CONNECTION_URL)
  db = SQLDatabase(engine)
  

  You might need to adapt this approach to your specific use case¹.
• Ensure that your langchain version (0.1.5) is compatible with your environment and dependencies. Sometimes, upgrading to a newer version might resolve issues.
• If you encounter any other issues, feel free to ask!

[Octavian1]

Hi @Kaniz 

You may be right regarding SQLAlchemy, the trace hints at something related:

> /lib/python3.10/site-packages/langchain_community/utilities/sql_database.py", line 133, in from_uri

> """Construct a SQLAlchemy engine from URI."""

But I don't get why in the SQLDatabase.from_databricks documentation there is no mention of any port parameter, neither in the example notebooks?

Thanks,

Octavian