langchain/cookbook/databricks_sql_db.ipynb

Databricks

This notebook covers how to connect to the Databricks runtimes and Databricks SQL using the SQLDatabase wrapper of LangChain. It is broken into 3 parts: installation and setup, connecting to Databricks, and examples.

Installation and Setup

In [1]:

!pip install databricks-sql-connector

Connecting to Databricks

You can connect to Databricks runtimes and Databricks SQL using the SQLDatabase.from_databricks() method.

Syntax

SQLDatabase.from_databricks(
    catalog: str,
    schema: str,
    host: Optional[str] = None,
    api_token: Optional[str] = None,
    warehouse_id: Optional[str] = None,
    cluster_id: Optional[str] = None,
    engine_args: Optional[dict] = None,
    **kwargs: Any)

Required Parameters

• catalog: The catalog name in the Databricks database.
• schema: The schema name in the catalog.

Optional Parameters

There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.

• host: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.
• api_token: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.
• warehouse_id: The warehouse ID in the Databricks SQL.
• cluster_id: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.
• engine_args: The arguments to be used when connecting Databricks.
• **kwargs: Additional keyword arguments for the SQLDatabase.from_uri method.

Examples

In [2]:

# Connecting to Databricks with SQLDatabase wrapper
from langchain_community.utilities import SQLDatabase

db = SQLDatabase.from_databricks(catalog="samples", schema="nyctaxi")

In [3]:

# Creating a OpenAI Chat LLM wrapper
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0, model_name="gpt-4")

SQL Chain example

This example demonstrates the use of the SQL Chain for answering a question over a Databricks database.

In [4]:

from langchain_community.utilities import SQLDatabaseChain

db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)

In [5]:

db_chain.run(
    "What is the average duration of taxi rides that start between midnight and 6am?"
)

Out [5]:

> Entering new SQLDatabaseChain chain...
What is the average duration of taxi rides that start between midnight and 6am?
SQLQuery:SELECT AVG(UNIX_TIMESTAMP(tpep_dropoff_datetime) - UNIX_TIMESTAMP(tpep_pickup_datetime)) as avg_duration
FROM trips
WHERE HOUR(tpep_pickup_datetime) >= 0 AND HOUR(tpep_pickup_datetime) < 6
SQLResult: [(987.8122786304605,)]
Answer:The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.
> Finished chain.

'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'

SQL Database Agent example

This example demonstrates the use of the SQL Database Agent for answering questions over a Databricks database.

In [7]:

from langchain.agents import create_sql_agent
from langchain_community.agent_toolkits import SQLDatabaseToolkit

toolkit = SQLDatabaseToolkit(db=db, llm=llm)
agent = create_sql_agent(llm=llm, toolkit=toolkit, verbose=True)

In [8]:

agent.run("What is the longest trip distance and how long did it take?")

Out [8]:

> Entering new AgentExecutor chain...
Action: list_tables_sql_db
Action Input: 
Observation: trips
Thought:I should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.
Action: schema_sql_db
Action Input: trips
Observation: 
CREATE TABLE trips (
	tpep_pickup_datetime TIMESTAMP, 
	tpep_dropoff_datetime TIMESTAMP, 
	trip_distance FLOAT, 
	fare_amount FLOAT, 
	pickup_zip INT, 
	dropoff_zip INT
) USING DELTA

/*
3 rows from trips table:
tpep_pickup_datetime	tpep_dropoff_datetime	trip_distance	fare_amount	pickup_zip	dropoff_zip
2016-02-14 16:52:13+00:00	2016-02-14 17:16:04+00:00	4.94	19.0	10282	10171
2016-02-04 18:44:19+00:00	2016-02-04 18:46:00+00:00	0.28	3.5	10110	10110
2016-02-17 17:13:57+00:00	2016-02-17 17:17:55+00:00	0.7	5.0	10103	10023
*/
Thought:The trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.
Action: query_checker_sql_db
Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1
Observation: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1
Thought:The query is correct. I will now execute it to find the longest trip distance and its duration.
Action: query_sql_db
Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1
Observation: [(30.6, '0 00:43:31.000000000')]
Thought:I now know the final answer.
Final Answer: The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.

> Finished chain.

'The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.'