How to Query Live PingOne Data in Natural Language in Python using LlamaIndex

Use LlamaIndex to query live PingOne data data in natural language using Python.

Start querying live data from PingOne using the CData Python Connector for PingOne. Leverage the power of AI with LlamaIndex and retrieve insights using simple English, eliminating the need for complex SQL queries. Benefit from real-time data access that enhances your decision-making process, while easily integrating with your existing Python applications.

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

Whether you're analyzing trends, generating reports, or visualizing data, our Python connectors enable you to harness the full potential of your live data source with ease.

Overview

Here's how to query live data with CData's Python connector for PingOne data using LlamaIndex:

Import required Python, CData, and LlamaIndex modules for logging, database connectivity, and NLP.
Retrieve your OpenAI API key for authenticating API requests from your application.
Connect to live PingOne data using the CData Python Connector.
Initialize OpenAI and create instances of SQLDatabase and NLSQLTableQueryEngine for handling natural language queries.
Create the query engine and specific database instance.
Execute natural language queries (e.g., "Who are the top-earning employees?") to get structured responses from the database.
Analyze retrieved data to gain insights and inform data-driven decisions.

Import Required Modules

Import the necessary modules CData, database connections, and natural language querying.


import os
import logging
import sys

# Configure logging
logging.basicConfig(stream=sys.stdout, level=logging.INFO, force=True)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

# Import required modules for CData and LlamaIndex
import cdata.pingone as mod
from sqlalchemy import create_engine
from llama_index.core.query_engine import NLSQLTableQueryEngine
from llama_index.core import SQLDatabase
from llama_index.llms.openai import OpenAI

Set Your OpenAI API Key

To use OpenAI's language model, you need to set your API key as an environment variable. Make sure you have your OpenAI API key available in your system's environment variables.


# Retrieve the OpenAI API key from the environment variables
OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]

''as an alternative, you can also add your API key directly within your code (though this method is not recommended for production environments due to security risks):''

# Directly set the API key (not recommended for production use)
OPENAI_API_KEY = "your-api-key-here"

Create a Database Connection

Next, establish a connection to PingOne using the CData connector using a connection string with the required connection properties.

To connect to PingOne, configure these properties:

Region: The region where the data for your PingOne organization is being hosted.
AuthScheme: The type of authentication to use when connecting to PingOne.
Either WorkerAppEnvironmentId (required when using the default PingOne domain) or AuthorizationServerURL, configured as described below.

Configuring WorkerAppEnvironmentId

WorkerAppEnvironmentId is the ID of the PingOne environment in which your Worker application resides. This parameter is used only when the environment is using the default PingOne domain (auth.pingone). It is configured after you have created the custom OAuth application you will use to authenticate to PingOne, as described in Creating a Custom OAuth Application in the Help documentation.

First, find the value for this property:

From the home page of your PingOne organization, move to the navigation sidebar and click Environments.
Find the environment in which you have created your custom OAuth/Worker application (usually Administrators), and click Manage Environment. The environment's home page displays.
In the environment's home page navigation sidebar, click Applications.
Find your OAuth or Worker application details in the list.
Copy the value in the Environment ID field. It should look similar to:
WorkerAppEnvironmentId='11e96fc7-aa4d-4a60-8196-9acf91424eca'

Now set WorkerAppEnvironmentId to the value of the Environment ID field.

Configuring AuthorizationServerURL

AuthorizationServerURL is the base URL of the PingOne authorization server for the environment where your application is located. This property is only used when you have set up a custom domain for the environment, as described in the PingOne platform API documentation. See Custom Domains.

Authenticating to PingOne with OAuth

PingOne supports both OAuth and OAuthClient authentication. In addition to performing the configuration steps described above, there are two more steps to complete to support OAuth or OAuthCliet authentication:

Create and configure a custom OAuth application, as described in Creating a Custom OAuth Application in the Help documentation.
To ensure that the driver can access the entities in Data Model, confirm that you have configured the correct roles for the admin user/worker application you will be using, as described in Administrator Roles in the Help documentation.
Set the appropriate properties for the authscheme and authflow of your choice, as described in the following subsections.

OAuth (Authorization Code grant)

Set AuthScheme to OAuth.

Desktop Applications

Get and Refresh the OAuth Access Token

After setting the following, you are ready to connect:

InitiateOAuth: GETANDREFRESH. To avoid the need to repeat the OAuth exchange and manually setting the OAuthAccessToken each time you connect, use InitiateOAuth.
OAuthClientId: The Client ID you obtained when you created your custom OAuth application.
OAuthClientSecret: The Client Secret you obtained when you created your custom OAuth application.
CallbackURL: The redirect URI you defined when you registered your custom OAuth application. For example: https://localhost:3333

When you connect, the driver opens PingOne's OAuth endpoint in your default browser. Log in and grant permissions to the application. The driver then completes the OAuth process:

The driver obtains an access token from PingOne and uses it to request data.
The OAuth values are saved in the location specified in OAuthSettingsLocation, to be persisted across connections.

The driver refreshes the access token automatically when it expires.

For other OAuth methods, including Web Applications, Headless Machines, or Client Credentials Grant, refer to the Help documentation.

Connecting to PingOne


# Create a database engine using the CData Python Connector for PingOne
engine = create_engine("cdata_pingone_2:///?User=AuthScheme=OAuth;WorkerAppEnvironmentId=eebc33a8-xxxx-4f3a-yyyy-d3e5262fd49e;Region=NA;OAuthClientId=client_id;OAuthClientSecret=client_secret;")

Initialize the OpenAI Instance

Create an instance of the OpenAI language model. Here, you can specify parameters like temperature and the model version.


# Initialize the OpenAI language model instance
llm = OpenAI(temperature=0.0, model="gpt-3.5-turbo")

Set Up the Database and Query Engine

Now, set up the SQL database and the query engine. The NLSQLTableQueryEngine allows you to perform natural language queries against your SQL database.


# Create a SQL database instance
sql_db = SQLDatabase(engine)  # This includes all tables

# Initialize the query engine for natural language SQL queries
query_engine = NLSQLTableQueryEngine(sql_database=sql_db)

Execute a Query

Now, you can execute a natural language query against your live data source. In this example, we will query for the top two earning employees.


# Define your query string
query_str = "Who are the top earning employees?"

# Get the response from the query engine
response = query_engine.query(query_str)

# Print the response
print(response)

Download a free, 30-day trial of the CData Python Connector for PingOne and start querying your live data seamlessly. Experience the power of natural language processing and unlock valuable insights from your data today.

Ready to get started?

Download a free trial of the PingOne Connector to get started:

Download Now

Learn more:

PingOne Python Connector

Python Connector Libraries for PingOne Data Connectivity. Integrate PingOne with popular Python tools like Pandas, SQLAlchemy, Dash & petl.