langchain
langchain copied to clipboard
Support Databricks in SQLDatabase
This PR adds support for Databricks runtime and Databricks SQL by using Databricks SQL Connector for Python.
As a cloud data platform, accessing Databricks requires a URL as follows
databricks://token:{api_token}@{hostname}?http_path={http_path}&catalog={catalog}&schema={schema}.
The URL is complicated and it may take users a while to figure it out. Since the fields api_token/hostname/http_path fields are known in the Databricks notebook, I am proposing a new method from_databricks to simplify the connection to Databricks.
In Databricks Notebook
After changes, Databricks users only need to specify the catalog and schema field when using langchain.
In Jupyter Notebook
The method can be used on the local setup as well:
cc @vowelparrot @hwchase17 @mengxr