Azure Logic Apps integration

This page covers the Azure Logic Apps integration from langchain_azure_ai.tools.

Azure Logic Apps is a cloud service that helps you automate workflows and business processes. You can use the AzureLogicAppTool to invoke pre-configured Logic App workflows from your LangChain agents, enabling automation, notifications, data synchronization, and orchestration of multi-step processes.

Overview

The AzureLogicAppTool allows agents to trigger Azure Logic Apps workflows by sending JSON payloads to named triggers. This is useful for automating tasks like sending emails, processing data, calling APIs, or integrating with other Azure and third-party services.

Common use cases:

1. Email notifications - Send alerts and notifications via Logic App
2. Data synchronization - Sync data between systems
3. Order processing - Trigger order fulfillment workflows
4. API integrations - Call external APIs through Logic Apps
5. Approval workflows - Start approval processes
6. Data transformation - Process and transform data
7. Multi-step automation - Orchestrate complex business processes

Setup

Install the integration package and configure your Azure credentials.

Installation

Install the package with the tools extra:

pip install -U "langchain-azure-ai[tools]"

uv add "langchain-azure-ai[tools]"

This extra installs the required azure-mgmt-logic dependency.

Prerequisites

Before using this tool, you need:

1. An Azure subscription
2. An Azure Logic App with at least one HTTP request trigger
3. The subscription ID, resource group name, Logic App name, and trigger name

Credentials

The tool uses DefaultAzureCredential() by default, which supports various authentication methods including environment variables, managed identity, and interactive login.

from azure.identity import DefaultAzureCredential

credential = DefaultAzureCredential()

You can also pass a specific credential explicitly:

from azure.identity import ManagedIdentityCredential

credential = ManagedIdentityCredential()

Basic usage

Instantiate the tool

from langchain_azure_ai.tools import AzureLogicAppTool

tool = AzureLogicAppTool(
    subscription_id="<your-subscription-id>",
    resource_group="<your-resource-group>",
    logic_app_name="<your-logic-app-name>",
    trigger_name="<your-trigger-name>",
)

Invoke the tool

import json

# Simple text input
result = tool.invoke("Send an email notification")
print(result)

# JSON payload input
payload = {
    "email": "user@example.com",
    "subject": "Test Email",
    "message": "This is a test message from a Logic App trigger."
}
result = tool.invoke(json.dumps(payload))
print(result)

Use with an agent

Pass the tool to create_agent.

from azure.identity import DefaultAzureCredential
from langchain.agents import create_agent
from langchain.chat_models import init_chat_model
from langchain_azure_ai.tools import AzureLogicAppTool

credential = DefaultAzureCredential()
tool = AzureLogicAppTool(
    subscription_id="<your-subscription-id>",
    resource_group="<your-resource-group>",
    logic_app_name="notification-workflow",
    trigger_name="manual_trigger",
    credential=credential,
)

agent = create_agent(
    model=init_chat_model("azure_ai:gpt-4.1", credential=credential),
    tools=[tool],
    system_prompt=(
        "You are a workflow automation assistant. Use the Logic Apps tool to trigger "
        "workflows for sending notifications, processing data, or integrating with "
        "other services when users request automation tasks."
    ),
)

Configuration

Parameters

Input format

The tool accepts input as either:

1. Plain text - Automatically converted to JSON with an input key
2. JSON string - Parsed and sent as-is to the Logic App trigger

Examples

# Plain text input
tool.invoke("Process this order")
# Sent as: {"input": "Process this order"}

# JSON payload
import json
payload = {
    "orderId": "12345",
    "customerEmail": "customer@example.com",
    "items": ["item1", "item2"]
}
tool.invoke(json.dumps(payload))

Response format

The tool returns a JSON response indicating success or failure:

{
  "result": "Successfully invoked <logic-app-name>."
}

Or on error:

{
  "error": "Error invoking <logic-app-name> (HTTP_STATUS): ERROR_DETAILS"
}

API reference

from langchain_azure_ai.tools import AzureLogicAppTool