How to use SQLAlchemy ORM to access Claude Compliance Data in Python

The rich ecosystem of Python modules lets you get to work quickly and integrate your systems effectively. With the CData Python Connector for Claude Compliance and the SQLAlchemy toolkit, you can build Claude Compliance-connected Python applications and scripts. This article shows how to use SQLAlchemy to connect to Claude Compliance data to query Claude Compliance data.

With built-in optimized data processing, the CData Python Connector offers unmatched performance for interacting with live Claude Compliance data in Python. When you issue complex SQL queries from Claude Compliance, the CData Connector pushes supported SQL operations, like filters and aggregations, directly to Claude Compliance and utilizes the embedded SQL engine to process unsupported operations client-side (often SQL functions and JOIN operations).

Connecting to Claude Compliance Data

Connecting to Claude Compliance data looks just like connecting to any relational data source. Create a connection string using the required connection properties. For this article, you will pass the connection string as a parameter to the create_engine function.

The driver connects to Claude Compliance using a Compliance Access Key, the only supported authentication method. Set the following connection property:

• APIKey: The Compliance Access Key you created.

Creating a Compliance Access Key

1. Enable the Compliance API for your organization.
2. Sign in to claude.ai as a primary owner or organization owner and open Organization settings > API > Keys.
3. Select Create Key and assign only the scopes your integration needs:
   • read:compliance_activities for Activities and the typed activity views.
   • read:compliance_org_data for organizations, roles, groups, and settings.
   • read:compliance_user_data for users, chats, files, projects, and downloads.
   • delete:compliance_user_data for the explicit Delete stored procedures.
4. Create the key and copy it when it appears. The key starts with sk-ant-api01- and is shown only once.

Optionally, set OrganizationUUID to limit organization-scoped views (such as OrganizationUsers and ComplianceRoles) to a single linked organization. If it is left empty, those views default to the first available organization and do not include data from all linked organizations.

Follow the procedure below to install SQLAlchemy and start accessing Claude Compliance through Python objects.

Install Required Modules

Use the pip utility to install the SQLAlchemy toolkit and SQLAlchemy ORM package:

pip install sqlalchemy
pip install sqlalchemy.orm

Be sure to import the appropriate modules:

from sqlalchemy import create_engine, String, Column
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker

Model Claude Compliance Data in Python

You can now connect with a connection string. Use the create_engine function to create an Engine for working with Claude Compliance data.

NOTE: Users should URL encode the any connection string properties that include special characters. For more information, refer to the SQL Alchemy documentation.

engine = create_engine("claudecompliance:///?APIKey=your_compliance_access_key")

Declare a Mapping Class for Claude Compliance Data

After establishing the connection, declare a mapping class for the table you wish to model in the ORM (in this article, we will model the Projects table). Use the sqlalchemy.ext.declarative.declarative_base function and create a new class with some or all of the fields (columns) defined.

base = declarative_base()
class Projects(base):
	__tablename__ = "Projects"
	Id = Column(String,primary_key=True)
	Name = Column(String)
	...

Query Claude Compliance Data

With the mapping class prepared, you can use a session object to query the data source. After binding the Engine to the session, provide the mapping class to the session query method.

Using the query Method

engine = create_engine("claudecompliance:///?APIKey=your_compliance_access_key")
factory = sessionmaker(bind=engine)
session = factory()
for instance in session.query(Projects).filter_by(OrganizationUuid="abcdef01-2345-6789-abcd-ef0123456789"):
	print("Id: ", instance.Id)
	print("Name: ", instance.Name)
	print("---------")

Alternatively, you can use the execute method with the appropriate table object. The code below works with an active session.

Using the execute Method

Projects_table = Projects.metadata.tables["Projects"]
for instance in session.execute(Projects_table.select().where(Projects_table.c.OrganizationUuid == "abcdef01-2345-6789-abcd-ef0123456789")):
	print("Id: ", instance.Id)
	print("Name: ", instance.Name)
	print("---------")

For examples of more complex querying, including JOINs, aggregations, limits, and more, refer to the Help documentation for the extension.

Free Trial & More Information

Download a free, 30-day trial of the CData Python Connector for Claude Compliance to start building Python apps and scripts with connectivity to Claude Compliance data. Reach out to our Support Team if you have any questions.