Use the Microsoft Fabric data agent (preview)

import os
from dotenv import load_dotenv
from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import (
    PromptAgentDefinition,
    MicrosoftFabricAgentTool,
    FabricDataAgentToolParameters,
    ToolProjectConnection,
)

load_dotenv()

project_client = AIProjectClient(
    endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
    credential=DefaultAzureCredential(),
)

openai_client = project_client.get_openai_client()

with project_client:
    agent = project_client.agents.create_version(
        agent_name="MyAgent",
        definition=PromptAgentDefinition(
            model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
            instructions="You are a helpful assistant.",
            tools=[
                MicrosoftFabricAgentTool(
                    fabric_dataagent_preview=FabricDataAgentToolParameters(
                        project_connections=[
                            ToolProjectConnection(project_connection_id=os.environ["FABRIC_PROJECT_CONNECTION_ID"])
                        ]
                    )
                )
            ],
        ),
    )
    print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")

    user_input = input("Enter your question for Fabric (e.g., 'Tell me about sales records'): \n")

    response = openai_client.responses.create(
        tool_choice="required",
        input=user_input,
        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
    )

    print(f"Response output: {response.output_text}")

For more details, see the full Python sample for Fabric data agent.

The following example shows how to call the Foundry Agent REST API by using the Fabric data agent tool.

curl --request POST \
  --url "$AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/openai/responses?api-version=$API_VERSION" \
  --H "Authorization: Bearer $AGENT_TOKEN" \
  --H "Content-Type: application/json" \
  --H "User-Agent: insomnia/11.6.1" \
  --d '{
"model": "$AZURE_AI_MODEL_DEPLOYMENT_NAME",
"input": "Tell me about sales records for the last quarter.",
"tools": [
  {
   "type": "fabric_dataagent_preview",
   "fabric_dataagent_preview": [
        {
            "project_connections": [
                {
                    "project_connection_id": "/subscriptions/${SUBSCRIPTION_ID}/resourceGroups/${RESOURCE_GROUP}/providers/Microsoft.CognitiveServices/accounts/${AI_SERVICES_NAME}/projects/${PROJECT_NAME}/connections/${FABRIC_PROJECT_CONNECTION_ID}"
                }
                ]
        }
        ]
    }
    ]
}'

The following TypeScript example demonstrates how to create an AI agent with Microsoft Fabric capabilities using the MicrosoftFabricAgentTool and synchronous Azure AI Projects client. The agent can query Fabric data sources and provide responses based on data analysis. For a JavaScript version of this sample, see the JavaScript sample for Fabric data agent in the Azure SDK for JavaScript repository on GitHub.

import { DefaultAzureCredential } from "@azure/identity";
import { AIProjectClient } from "@azure/ai-projects";
import * as readline from "readline";
import "dotenv/config";

const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
const fabricProjectConnectionId =
  process.env["FABRIC_PROJECT_CONNECTION_ID"] || "<fabric project connection id>";

export async function main(): Promise<void> {
  const project = new AIProjectClient(projectEndpoint, new DefaultAzureCredential());
  const openAIClient = await project.getOpenAIClient();

  console.log("Creating agent with Microsoft Fabric tool...");

  // Define Microsoft Fabric tool that connects to Fabric data sources
  const agent = await project.agents.createVersion("MyFabricAgent", {
    kind: "prompt",
    model: deploymentName,
    instructions: "You are a helpful assistant.",
    tools: [
      {
        type: "fabric_dataagent_preview",
        fabric_dataagent_preview: {
          project_connections: [
            {
              project_connection_id: fabricProjectConnectionId,
            },
          ],
        },
      },
    ],
  });
  console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);

  // Prompt user for input
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
  });

  const userInput = await new Promise<string>((resolve) => {
    rl.question(
      "Enter your question for Fabric (e.g., 'Tell me about sales records'): \n",
      (answer) => {
        rl.close();
        resolve(answer);
      },
    );
  });

  console.log("\nSending request to Fabric agent...");
  const response = await openAIClient.responses.create(
    {
      input: userInput,
    },
    {
      body: {
        agent: { name: agent.name, type: "agent_reference" },
        tool_choice: "required",
      },
    },
  );

  console.log(`\nResponse output: ${response.output_text}`);

  // Clean up resources by deleting the agent version
  // This prevents accumulation of unused resources in your project
  console.log("\nCleaning up resources...");
  await project.agents.deleteVersion(agent.name, agent.version);
  console.log("Agent deleted");

  console.log("\nMicrosoft Fabric agent sample completed!");
}

main().catch((err) => {
  console.error("The sample encountered an error:", err);
});