Cloud SQL is a fully managed relational database service that offers high performance, seamless integration, and impressive scalability. It offersMySQL,PostgreSQL, andSQL Server database engines. Extend your database application to build AI-powered experiences leveraging Cloud SQL's Langchain integrations.

This notebook goes over how to useCloud SQL for MySQL tosave, load and delete langchain documents withMySQLLoader andMySQLDocumentSaver.

Learn more about the package onGitHub.

Before You Begin​

To run this notebook, you will need to do the following:

• Create a Google Cloud Project
• Enable the Cloud SQL Admin API.
• Create a Cloud SQL for MySQL instance
• Create a Cloud SQL database
• Add an IAM database user to the database (Optional)

After confirmed access to database in the runtime environment of this notebook, filling the following values and run the cell before running example scripts.

# @markdown Please fill in the both the Google Cloud region and name of your Cloud SQL instance.
REGION="us-central1"# @param {type:"string"}
INSTANCE="test-instance"# @param {type:"string"}

# @markdown Please specify a database and a table for demo purpose.
DATABASE="test"# @param {type:"string"}
TABLE_NAME="test-default"# @param {type:"string"}

🦜🔗 Library Installation​

The integration lives in its ownlangchain-google-cloud-sql-mysql package, so we need to install it.

%pip install-upgrade--quiet langchain-google-cloud-sql-mysql

Colab only: Uncomment the following cell to restart the kernel or use the button to restart the kernel. For Vertex AI Workbench you can restart the terminal using the button on top.

# # Automatically restart kernel after installs so that your environment can access the new packages
# import IPython

# app = IPython.Application.instance()
# app.kernel.do_shutdown(True)

☁ Set Your Google Cloud Project​

Set your Google Cloud project so that you can leverage Google Cloud resources within this notebook.

If you don't know your project ID, try the following:

• Rungcloud config list.
• Rungcloud projects list.
• See the support page:Locate the project ID.

# @markdown Please fill in the value below with your Google Cloud project ID and then run the cell.

PROJECT_ID="my-project-id"# @param {type:"string"}

# Set the project id
!gcloud configset project{PROJECT_ID}

🔐 Authentication​

Authenticate to Google Cloud as the IAM user logged into this notebook in order to access your Google Cloud Project.

• If you are using Colab to run this notebook, use the cell below and continue.
• If you are using Vertex AI Workbench, check out the setup instructionshere.

from google.colabimport auth

auth.authenticate_user()

Basic Usage​

MySQLEngine Connection Pool​

Before saving or loading documents from MySQL table, we need first configures a connection pool to Cloud SQL database. TheMySQLEngine configures a connection pool to your Cloud SQL database, enabling successful connections from your application and following industry best practices.

To create aMySQLEngine usingMySQLEngine.from_instance() you need to provide only 4 things:

1. project_id : Project ID of the Google Cloud Project where the Cloud SQL instance is located.
2. region : Region where the Cloud SQL instance is located.
3. instance : The name of the Cloud SQL instance.
4. database : The name of the database to connect to on the Cloud SQL instance.

By default,IAM database authentication will be used as the method of database authentication. This library uses the IAM principal belonging to theApplication Default Credentials (ADC) sourced from the envionment.

For more informatin on IAM database authentication please see:

• Configure an instance for IAM database authentication
• Manage users with IAM database authentication

Optionally,built-in database authentication using a username and password to access the Cloud SQL database can also be used. Just provide the optionaluser andpassword arguments toMySQLEngine.from_instance():

• user : Database user to use for built-in database authentication and login
• password : Database password to use for built-in database authentication and login.

from langchain_google_cloud_sql_mysqlimport MySQLEngine

engine= MySQLEngine.from_instance(
    project_id=PROJECT_ID, region=REGION, instance=INSTANCE, database=DATABASE
)

Initialize a table​

Initialize a table of default schema viaMySQLEngine.init_document_table(<table_name>). Table Columns:

• page_content (type: text)
• langchain_metadata (type: JSON)

overwrite_existing=True flag means the newly initialized table will replace any existing table of the same name.

engine.init_document_table(TABLE_NAME, overwrite_existing=True)

Save documents​

Save langchain documents withMySQLDocumentSaver.add_documents(<documents>). To initializeMySQLDocumentSaver class you need to provide 2 things:

1. engine - An instance of aMySQLEngine engine.
2. table_name - The name of the table within the Cloud SQL database to store langchain documents.

from langchain_core.documentsimport Document
from langchain_google_cloud_sql_mysqlimport MySQLDocumentSaver

test_docs=[
    Document(
        page_content="Apple Granny Smith 150 0.99 1",
        metadata={"fruit_id":1},
),
    Document(
        page_content="Banana Cavendish 200 0.59 0",
        metadata={"fruit_id":2},
),
    Document(
        page_content="Orange Navel 80 1.29 1",
        metadata={"fruit_id":3},
),
]
saver= MySQLDocumentSaver(engine=engine, table_name=TABLE_NAME)
saver.add_documents(test_docs)

Load documents​

Load langchain documents withMySQLLoader.load() orMySQLLoader.lazy_load().lazy_load returns a generator that only queries database during the iteration. To initializeMySQLLoader class you need to provide:

1. engine - An instance of aMySQLEngine engine.
2. table_name - The name of the table within the Cloud SQL database to store langchain documents.

from langchain_google_cloud_sql_mysqlimport MySQLLoader

loader= MySQLLoader(engine=engine, table_name=TABLE_NAME)
docs= loader.lazy_load()
for docin docs:
print("Loaded documents:", doc)

Load documents via query​

Other than loading documents from a table, we can also choose to load documents from a view generated from a SQL query. For example:

from langchain_google_cloud_sql_mysqlimport MySQLLoader

loader= MySQLLoader(
    engine=engine,
    query=f"select * from `{TABLE_NAME}` where JSON_EXTRACT(langchain_metadata, '$.fruit_id') = 1;",
)
onedoc= loader.load()
onedoc

The view generated from SQL query can have different schema than default table. In such cases, the behavior of MySQLLoader is the same as loading from table with non-default schema. Please refer to sectionLoad documents with customized document page content & metadata.

Delete documents​

Delete a list of langchain documents from MySQL table withMySQLDocumentSaver.delete(<documents>).

For table with default schema (page_content, langchain_metadata), the deletion criteria is:

Arow should be deleted if there exists adocument in the list, such that

• document.page_content equalsrow[page_content]
• document.metadata equalsrow[langchain_metadata]

from langchain_google_cloud_sql_mysqlimport MySQLLoader

loader= MySQLLoader(engine=engine, table_name=TABLE_NAME)
docs= loader.load()
print("Documents before delete:", docs)
saver.delete(onedoc)
print("Documents after delete:", loader.load())

Advanced Usage​

Load documents with customized document page content & metadata​

First we prepare an example table with non-default schema, and populate it with some arbitrary data.

import sqlalchemy

with engine.connect()as conn:
    conn.execute(sqlalchemy.text(f"DROP TABLE IF EXISTS `{TABLE_NAME}`"))
    conn.commit()
    conn.execute(
        sqlalchemy.text(
f"""
            CREATE TABLE IF NOT EXISTS `{TABLE_NAME}`(
                fruit_id INT AUTO_INCREMENT PRIMARY KEY,
                fruit_name VARCHAR(100) NOT NULL,
                variety VARCHAR(50),
                quantity_in_stock INT NOT NULL,
                price_per_unit DECIMAL(6,2) NOT NULL,
                organic TINYINT(1) NOT NULL
            )
            """
)
)
    conn.execute(
        sqlalchemy.text(
f"""
            INSERT INTO `{TABLE_NAME}` (fruit_name, variety, quantity_in_stock, price_per_unit, organic)
            VALUES
                ('Apple', 'Granny Smith', 150, 0.99, 1),
                ('Banana', 'Cavendish', 200, 0.59, 0),
                ('Orange', 'Navel', 80, 1.29, 1);
            """
)
)
    conn.commit()

If we still load langchain documents with default parameters ofMySQLLoader from this example table, thepage_content of loaded documents will be the first column of the table, andmetadata will be consisting of key-value pairs of all the other columns.

loader= MySQLLoader(
    engine=engine,
    table_name=TABLE_NAME,
)
loader.load()

We can specify the content and metadata we want to load by setting thecontent_columns andmetadata_columns when initializing theMySQLLoader.

1. content_columns: The columns to write into thepage_content of the document.
2. metadata_columns: The columns to write into themetadata of the document.

For example here, the values of columns incontent_columns will be joined together into a space-separated string, aspage_content of loaded documents, andmetadata of loaded documents will only contain key-value pairs of columns specified inmetadata_columns.

loader= MySQLLoader(
    engine=engine,
    table_name=TABLE_NAME,
    content_columns=[
"variety",
"quantity_in_stock",
"price_per_unit",
"organic",
],
    metadata_columns=["fruit_id","fruit_name"],
)
loader.load()

Save document with customized page content & metadata​

In order to save langchain document into table with customized metadata fields. We need first create such a table viaMySQLEngine.init_document_table(), and specify the list ofmetadata_columns we want it to have. In this example, the created table will have table columns:

• description (type: text): for storing fruit description.
• fruit_name (type text): for storing fruit name.
• organic (type tinyint(1)): to tell if the fruit is organic.
• other_metadata (type: JSON): for storing other metadata information of the fruit.

We can use the following parameters withMySQLEngine.init_document_table() to create the table:

1. table_name: The name of the table within the Cloud SQL database to store langchain documents.
2. metadata_columns: A list ofsqlalchemy.Column indicating the list of metadata columns we need.
3. content_column: The name of column to storepage_content of langchain document. Default:page_content.
4. metadata_json_column: The name of JSON column to store extrametadata of langchain document. Default:langchain_metadata.

engine.init_document_table(
    TABLE_NAME,
    metadata_columns=[
        sqlalchemy.Column(
"fruit_name",
            sqlalchemy.UnicodeText,
            primary_key=False,
            nullable=True,
),
        sqlalchemy.Column(
"organic",
            sqlalchemy.Boolean,
            primary_key=False,
            nullable=True,
),
],
    content_column="description",
    metadata_json_column="other_metadata",
    overwrite_existing=True,
)

Save documents withMySQLDocumentSaver.add_documents(<documents>). As you can see in this example,

• document.page_content will be saved intodescription column.
• document.metadata.fruit_name will be saved intofruit_name column.
• document.metadata.organic will be saved intoorganic column.
• document.metadata.fruit_id will be saved intoother_metadata column in JSON format.

test_docs=[
    Document(
        page_content="Granny Smith 150 0.99",
        metadata={"fruit_id":1,"fruit_name":"Apple","organic":1},
),
]
saver= MySQLDocumentSaver(
    engine=engine,
    table_name=TABLE_NAME,
    content_column="description",
    metadata_json_column="other_metadata",
)
saver.add_documents(test_docs)

with engine.connect()as conn:
    result= conn.execute(sqlalchemy.text(f"select * from `{TABLE_NAME}`;"))
print(result.keys())
print(result.fetchall())

Delete documents with customized page content & metadata​

We can also delete documents from table with customized metadata columns viaMySQLDocumentSaver.delete(<documents>). The deletion criteria is:

Arow should be deleted if there exists adocument in the list, such that

• document.page_content equalsrow[page_content]
• For every metadata fieldk indocument.metadata
  • document.metadata[k] equalsrow[k] ordocument.metadata[k] equalsrow[langchain_metadata][k]
• There no extra metadata field presents inrow but not indocument.metadata.

loader= MySQLLoader(engine=engine, table_name=TABLE_NAME)
docs= loader.load()
print("Documents before delete:", docs)
saver.delete(docs)
print("Documents after delete:", loader.load())

Related​

• Document loaderconceptual guide
• Document loaderhow-to guides