Use ChatGPT to Talk to Your SQL Analysis Services Data via CData Connect AI

ChatGPT is an AI chatbot developed by OpenAI, launched in November 2022. Based on large language models (LLMs), it enables users to refine and steer conversations through natural language processing. ChatGPT's developer mode, available to Plus and Pro subscribers, provides full Model Context Protocol (MCP) support for connecting to external data sources and tools.

CData Connect AI offers a dedicated cloud-to-cloud interface for connecting to SQL Analysis Services data. The CData Connect AI Remote MCP Server enables secure communication between ChatGPT and SQL Analysis Services. This allows you to ask questions and take actions on your SQL Analysis Services data using ChatGPT, all without the need for data replication to a natively supported database. With its inherent optimized data processing capabilities, CData Connect AI efficiently channels all supported SQL operations, including filters and JOINs, directly to SQL Analysis Services. This leverages server-side processing to swiftly deliver the requested SQL Analysis Services data.

Step 1: Configure SQL Analysis Services Connectivity for ChatGPT

Connectivity to SQL Analysis Services from ChatGPT is made possible through CData Connect AI Remote MCP. To interact with SQL Analysis Services data from ChatGPT, we start by creating and configuring a SQL Analysis Services connection in CData Connect AI.

1. Log into your Connect AI account, click Sources, and then click Add Connection.

2. Select "SQL Analysis Services" from the Add Connection panel.

3. Enter the necessary authentication properties to connect to SQL Analysis Services.

   To connect, provide authentication and set the Url property to a valid SQL Server Analysis Services endpoint. You can connect to SQL Server Analysis Services instances hosted over HTTP with XMLA access. See the Microsoft documentation to configure HTTP access to SQL Server Analysis Services.

   To secure connections and authenticate, set the corresponding connection properties, below. The data provider supports the major authentication schemes, including HTTP and Windows, as well as SSL/TLS.

   • HTTP Authentication

     Set AuthScheme to "Basic" or "Digest" and set User and Password. Specify other authentication values in CustomHeaders.

   • Windows (NTLM)

     Set the Windows User and Password and set AuthScheme to "NTLM".

   • Kerberos and Kerberos Delegation

     To authenticate with Kerberos, set AuthScheme to NEGOTIATE. To use Kerberos delegation, set AuthScheme to KERBEROSDELEGATION. If needed, provide the User, Password, and KerberosSPN. By default, the data provider attempts to communicate with the SPN at the specified Url.

   • SSL/TLS:

     By default, the data provider attempts to negotiate SSL/TLS by checking the server's certificate against the system's trusted certificate store. To specify another certificate, see the SSLServerCert property for the available formats.

   You can then access any cube as a relational table: When you connect the data provider retrieves SSAS metadata and dynamically updates the table schemas. Instead of retrieving metadata every connection, you can set the CacheLocation property to automatically cache to a simple file-based store.

   See the Getting Started section of the CData documentation, under Retrieving Analysis Services Data, to execute SQL-92 queries to the cubes.

   
4. Click Save & Test

With the connection configured, we are ready to connect to SQL Analysis Services data from ChatGPT.

Step 2: Connect ChatGPT to CData Connect AI

Follow these steps to add a CData Connect AI connection in ChatGPT:

1. Sign in to ChatGPT with a Plus or Pro subscription.
2. Navigate to Apps from the left panel.
3. Select the CData Connect AI app from the list.
.
4. Click Connect to authenticate to your Connect AI account.

5. Click Sign in with CData Connect AI to add Connect AI to your ChatGPT account.

6. After successful authorization, you will be redirected back to ChatGPT.
7. Click Start Chat to start a new conversation in ChatGPT with Connect AI connected at the background.

Step 3: Explore Live SQL Analysis Services Data with ChatGPT

1. Start a new conversation in ChatGPT.
2. Connect AI should ideally be automatically enabled in the chat. If not, navigate to -> More -> CData Connect AI, under the chatbox, to enable the connector from the dropdown

3. You can now start exploring your data with natural language prompts. ChatGPT will use the Connect AI MCP server to query your live SQL Analysis Services data. Example prompts:
   • "Show me all customers from the last 30 days"
   • "What are my top performing products?"
   • "Analyze sales trends for this quarter"
   • "List all active projects and their current status"
   Refer to CData prompt library for more prompt ideas.

4. Permit ChatGPT to access your SQL Analysis Services data. Click Query Data to continue, or Deny to refuse.

5. ChatGPT translates your natural language queries into SQL and execute them against your SQL Analysis Services data through the Connect AI MCP server.

Get CData Connect AI

To get live data access to hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!