Use ChatGPT to Talk to Your API 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 API data. The CData Connect AI Remote MCP Server enables secure communication between ChatGPT and API. This allows you to ask questions and take actions on your API 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 API. This leverages server-side processing to swiftly deliver the requested API data.

Step 1: Configure your API Connectivity for ChatGPT

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

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

2. Select "API" from the Add Connection panel.
👁 Selecting a data source

3. Enter the necessary authentication properties to connect to your API.

   To connect to your API, configure the following properties on the Global Settings page:

   • In Authentication, select the Type and fill in the required properties
   • In Headers, add the required HTTP headers for your API
   • In Pagination, select the Type and fill in the required properties

   After the configuring the global settings, navigate to the Tables to add tables. For each table you wish to add:

   1. Click "+ Add"
   2. Set the Name for the table
   3. Set Request URL to the API endpoint you wish to work with 👁 Setting the Request URL (Harvest is shown)
      
   4. (Optional) In Parameters, add the required URL Parameters for your API endpoint
   5. (Optional) In Headers, add the required HTTP headers for the API endpoint
   6. In Table Data click " Configure"
   7. Review the response from the API and click "Next" 👁 Reviewing the API response (Harvest is shown)
      
   8. Select which element to use as the Repeated Elements and which elements to use as Columns and click "Next" 👁 Configuring the schema based on the API response(Harvest is shown)
      
   9. Preview the tabular model of the API response and click "Confirm" 👁 Previewing the tabular model of the API response (Harvest is shown)
      
4. Click Save & Test

With the connection configured, we are ready to connect to API 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.
. 👁 Search for CData Connect AI

4. Click Connect to authenticate to your Connect AI account.
👁 Click Connect to authenticate

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

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.
👁 Start Chat

Step 3: Explore Live API 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
👁 Enable CData Connect AI in the chat

3. You can now start exploring your data with natural language prompts. ChatGPT will use the Connect AI MCP server to query your live API 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.
👁 Using natural language to explore your API data (Salesforce used here).

4. Permit ChatGPT to access your API data. Click Query Data to continue, or Deny to refuse.
👁 Give permissions to ChatGPT.

5. ChatGPT translates your natural language queries into SQL and execute them against your API data through the Connect AI MCP server.
👁 ChatGPT shows the desired results from your API data based on the prompts

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!