langchain/docs/modules/chains/examples/sqlite.ipynb

SQLite example

This example showcases hooking up an LLM to answer questions over a database.

This uses the example Chinook database. To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the .db file in a notebooks folder at the root of this repository.

In [3]:

from langchain import OpenAI, SQLDatabase, SQLDatabaseChain

In [1]:

db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db")
llm = OpenAI(temperature=0)

NOTE: For data-sensitive projects, you can specify return_direct=True in the SQLDatabaseChain initialization to directly return the output of the SQL query without any additional formatting. This prevents the LLM from seeing any contents within the database. Note, however, the LLM still has access to the database scheme (i.e. dialect, table and key names) by default.

In [3]:

db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)

In [4]:

db_chain.run("How many employees are there?")

Out [4]:

> Entering new SQLDatabaseChain chain...
How many employees are there? 
SQLQuery: SELECT COUNT(*) FROM Employee;
SQLResult: [(8,)]
Answer: There are 8 employees.
> Finished chain.

' There are 8 employees.'

Customize Prompt

You can also customize the prompt that is used. Here is an example prompting it to understand that foobar is the same as the Employee table

In [5]:

from langchain.prompts.prompt import PromptTemplate

_DEFAULT_TEMPLATE = """Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.
Use the following format:

Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"

Only use the following tables:

{table_info}

If someone asks for the table foobar, they really mean the employee table.

Question: {input}"""
PROMPT = PromptTemplate(
    input_variables=["input", "table_info", "dialect"], template=_DEFAULT_TEMPLATE
)

In [6]:

db_chain = SQLDatabaseChain(llm=llm, database=db, prompt=PROMPT, verbose=True)

In [7]:

db_chain.run("How many employees are there in the foobar table?")

Out [7]:

> Entering new SQLDatabaseChain chain...
How many employees are there in the foobar table? 
SQLQuery: SELECT COUNT(*) FROM Employee;
SQLResult: [(8,)]
Answer: There are 8 employees in the foobar table.
> Finished chain.

' There are 8 employees in the foobar table.'

Return Intermediate Steps

You can also return the intermediate steps of the SQLDatabaseChain. This allows you to access the SQL statement that was generated, as well as the result of running that against the SQL Database.

In [8]:

db_chain = SQLDatabaseChain(llm=llm, database=db, prompt=PROMPT, verbose=True, return_intermediate_steps=True)

In [9]:

result = db_chain("How many employees are there in the foobar table?")
result["intermediate_steps"]

Out [9]:

> Entering new SQLDatabaseChain chain...
How many employees are there in the foobar table? 
SQLQuery: SELECT COUNT(*) FROM Employee;
SQLResult: [(8,)]
Answer: There are 8 employees in the foobar table.
> Finished chain.

[' SELECT COUNT(*) FROM Employee;', '[(8,)]']

Choosing how to limit the number of rows returned

If you are querying for several rows of a table you can select the maximum number of results you want to get by using the 'top_k' parameter (default is 10). This is useful for avoiding query results that exceed the prompt max length or consume tokens unnecessarily.

In [10]:

db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True, top_k=3)

In [11]:

db_chain.run("What are some example tracks by composer Johann Sebastian Bach?")

Out [11]:

> Entering new SQLDatabaseChain chain...
What are some example tracks by composer Johann Sebastian Bach? 
SQLQuery: SELECT Name, Composer FROM Track WHERE Composer = 'Johann Sebastian Bach' LIMIT 3;
SQLResult: [('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Johann Sebastian Bach'), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Johann Sebastian Bach'), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', 'Johann Sebastian Bach')]
Answer: Examples of tracks by composer Johann Sebastian Bach are 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', and 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude'.
> Finished chain.

' Examples of tracks by composer Johann Sebastian Bach are \'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\', \'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\', and \'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\'.'

Adding example rows from each table

Sometimes, the format of the data is not obvious and it is optimal to include a sample of rows from the tables in the prompt to allow the LLM to understand the data before providing a final query. Here we will use this feature to let the LLM know that artists are saved with their full names by providing two rows from the Track table.

In [13]:

db = SQLDatabase.from_uri(
    "sqlite:///../../../../notebooks/Chinook.db",
    include_tables=['Track'], # we include only one table to save tokens in the prompt :)
    sample_rows_in_table_info=2)

The sample rows are added to the prompt after each corresponding table's column information:

In [14]:

print(db.table_info)

CREATE TABLE [Album]
(
    [AlbumId] INTEGER  NOT NULL,
    [Title] NVARCHAR(160)  NOT NULL,
    [ArtistId] INTEGER  NOT NULL,
    CONSTRAINT [PK_Album] PRIMARY KEY  ([AlbumId]),
    FOREIGN KEY ([ArtistId]) REFERENCES [Artist] ([ArtistId]) 
		ON DELETE NO ACTION ON UPDATE NO ACTION
)

SELECT * FROM 'Album' LIMIT 2
AlbumId Title ArtistId
1 For Those About To Rock We Salute You 1
2 Balls to the Wall 2


CREATE TABLE [Track]
(
    [TrackId] INTEGER  NOT NULL,
    [Name] NVARCHAR(200)  NOT NULL,
    [AlbumId] INTEGER,
    [MediaTypeId] INTEGER  NOT NULL,
    [GenreId] INTEGER,
    [Composer] NVARCHAR(220),
    [Milliseconds] INTEGER  NOT NULL,
    [Bytes] INTEGER,
    [UnitPrice] NUMERIC(10,2)  NOT NULL,
    CONSTRAINT [PK_Track] PRIMARY KEY  ([TrackId]),
    FOREIGN KEY ([AlbumId]) REFERENCES [Album] ([AlbumId]) 
		ON DELETE NO ACTION ON UPDATE NO ACTION,
    FOREIGN KEY ([GenreId]) REFERENCES [Genre] ([GenreId]) 
		ON DELETE NO ACTION ON UPDATE NO ACTION,
    FOREIGN KEY ([MediaTypeId]) REFERENCES [MediaType] ([MediaTypeId]) 
		ON DELETE NO ACTION ON UPDATE NO ACTION
)

SELECT * FROM 'Track' LIMIT 2
TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice
1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99
2 Balls to the Wall 2 2 1 None 342562 5510424 0.99

In [15]:

db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)

In [16]:

db_chain.run("What are some example tracks by Bach?")

Out [16]:

> Entering new SQLDatabaseChain chain...
What are some example tracks by Bach? 
SQLQuery: SELECT Name FROM Track WHERE Composer LIKE '%Bach%' LIMIT 5;
SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]
Answer: Some example tracks by Bach are 'American Woman', 'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace', 'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria', 'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude', and 'Toccata and Fugue in D Minor, BWV 565: I. Toccata'.
> Finished chain.

' Some example tracks by Bach are \'American Woman\', \'Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace\', \'Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria\', \'Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude\', and \'Toccata and Fugue in D Minor, BWV 565: I. Toccata\'.'

SQLDatabaseSequentialChain

Chain for querying SQL database that is a sequential chain.

The chain is as follows:

1. Based on the query, determine which tables to use.
2. Based on those tables, call the normal SQL database chain.

This is useful in cases where the number of tables in the database is large.

In [3]:

from langchain.chains import SQLDatabaseSequentialChain

In [4]:

chain = SQLDatabaseSequentialChain.from_llm(llm, db, verbose=True)

In [5]:

chain.run("How many employees are also customers?")

Out [5]:

> Entering new SQLDatabaseSequentialChain chain...
Table names to use:
['Customer', 'Employee']

> Entering new SQLDatabaseChain chain...
How many employees are also customers? 
SQLQuery: SELECT COUNT(*) FROM Customer c INNER JOIN Employee e ON c.SupportRepId = e.EmployeeId;
SQLResult: [(59,)]
Answer: There are 59 employees who are also customers.
> Finished chain.

> Finished chain.

' There are 59 employees who are also customers.'