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

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

Start querying live data from JSON using the CData Python Connector for JSON. 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 JSON services in Python. When you issue complex SQL queries from Python, the driver pushes supported SQL operations, like filters and aggregations, directly to JSON 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 JSON services 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 JSON services 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.json 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 JSON using the CData connector using a connection string with the required connection properties.

See the Getting Started chapter in the data provider documentation to authenticate to your data source: The data provider models JSON APIs as bidirectional database tables and JSON files as read-only views (local files, files stored on popular cloud services, and FTP servers). The major authentication schemes are supported, including HTTP Basic, Digest, NTLM, OAuth, and FTP. See the Getting Started chapter in the data provider documentation for authentication guides.

After setting the URI and providing any authentication values, set DataModel to more closely match the data representation to the structure of your data.

The DataModel property is the controlling property over how your data is represented into tables and toggles the following basic configurations.

Document (default): Model a top-level, document view of your JSON data. The data provider returns nested elements as aggregates of data.
FlattenedDocuments: Implicitly join nested documents and their parents into a single table.
Relational: Return individual, related tables from hierarchical data. The tables contain a primary key and a foreign key that links to the parent document.

See the Modeling JSON Data chapter for more information on configuring the relational representation. You will also find the sample data used in the following examples. The data includes entries for people, the cars they own, and various maintenance services performed on those cars.

Connecting to JSON


# Create a database engine using the CData Python Connector for JSON
engine = create_engine("cdata_json_2:///?User=URI=C:/people.json;DataModel=Relational;")

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 JSON 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 JSON Connector to get started:

Download Now

Learn more:

JSON Python Connector

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

CData Software is a leading provider of data access and connectivity solutions. Our standards-based connectors streamline data access and insulate customers from the complexities of integrating with on-premise or cloud databases, SaaS, APIs, NoSQL, and Big Data.

Connect With Us

Get Started

Data Connectors

ETL/ ELT Solutions

Cloud & API Connectivity

OEM & Custom Drivers