feat: add customer support ticketing agent tutorial with structured output

google_adk_tutorials/structured_output_agent/customer_support_ticket_agent/README.md

@@ -0,0 +1,110 @@
+# 🎫 Customer Support Ticketing Agent with Structured Output
+
+A tutorial demonstrating how to implement a structured customer support ticketing system using Google's ADK (Agent Development Kit) framework. This example shows how to create type-safe, structured support tickets with priority levels, categories, and resolution estimates using Pydantic schemas and Gemini 2.0 Flash model.
+
+## Tutorial Features
+
+- 🎫 **Structured Support Tickets**: 
+  - Learn how to create comprehensive support ticket schemas
+  - Understand priority levels and categorization
+  - See how to estimate resolution times
+
+- 🔧 **Advanced Schema Design**: 
+  - Complex Pydantic models with enums and optional fields
+  - Proper field validation and descriptions
+  - Type-safe structured responses
+
+- 🎯 **Real-World Application**: 
+  - Practical customer support use case
+  - Shows how to handle different types of support requests
+  - Demonstrates structured output for business processes
+
+- 📊 **Priority Management**: 
+  - Four-tier priority system (Low, Medium, High, Critical)
+  - Automatic priority assignment based on issue description
+  - Category-based routing for different departments
+
+## How to Run
+
+1. **Setup Environment**
+   ```bash
+   # Clone the repository
+   git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
+   cd awesome-llm-apps/google_adk_tutorials/structured_output_agent/customer_support_ticket_agent
+
+   # Install dependencies
+   pip install -r requirements.txt
+   ```
+
+2. **Configure API Keys**
+   - Get Google AI API key from [Google AI Studio](https://aistudio.google.com/)
+   - Set up your API credentials for Gemini access
+
+3. **Run the Agent**
+   ```bash
+   # Start the ADK web interface from the root folder
+   cd google_adk_tutorials/structured_output_agent/customer_support_ticket_agent
+   adk web
+   ```
+   Then:
+   1. Open the web interface in your browser
+   2. Select the "support_ticket_creator" agent
+   3. Enter your support request (e.g., "I can't log into my account and I have an important meeting in 2 hours")
+   4. The response will be a structured JSON with all ticket details
+
+## Tutorial Overview
+
+This tutorial demonstrates advanced structured output implementation in Google ADK:
+
+1. **Complex Schema Design**: Learn how to create sophisticated Pydantic models
+2. **Enum Usage**: Understand how to use enums for constrained values
+3. **Optional Fields**: See how to handle optional data with proper defaults
+4. **Business Logic**: Learn how to implement real-world business processes
+
+## Code Structure
+
+- `customer_support_agent/agent.py`: Contains the main agent definition and SupportTicket schema
+- `customer_support_agent/__init__.py`: Module initialization for easy imports
+
+## Support Ticket Schema
+
+The agent creates structured tickets with the following fields:
+
+- **title**: Concise summary of the issue
+- **description**: Detailed problem description
+- **priority**: Priority level (low, medium, high, critical)
+- **category**: Department (Technical, Billing, Account, Product)
+- **steps_to_reproduce**: Optional list of steps for technical issues
+- **estimated_resolution_time**: Estimated time to resolve
+
+## Example Usage
+
+**Input**: "My payment failed and I'm getting charged twice for the same service"
+
+**Output**:
+```json
+{
+  "title": "Duplicate payment charge issue",
+  "description": "Customer reports payment failure followed by duplicate charges for the same service",
+  "priority": "high",
+  "category": "Billing",
+  "steps_to_reproduce": null,
+  "estimated_resolution_time": "4-6 hours"
+}
+```
+
+## Dependencies
+
+- `google-adk`: Google's Agent Development Kit
+- `pydantic`: Data validation and settings management
+
+## How Structured Output Works
+
+This tutorial shows how Google ADK handles complex structured output:
+
+1. **Input Processing**: Takes natural language support requests
+2. **Context Analysis**: Analyzes the issue severity and type
+3. **Structured Generation**: Creates comprehensive tickets with all required fields
+4. **Validation**: Ensures output matches the defined schema and business rules
+
+This approach demonstrates how to create reliable, business-ready structured responses in Google ADK applications. 

google_adk_tutorials/structured_output_agent/customer_support_ticket_agent/customer_support_agent/__init__.py

@@ -0,0 +1 @@
+from . import agent 

google_adk_tutorials/structured_output_agent/customer_support_ticket_agent/customer_support_agent/agent.py

@@ -0,0 +1,46 @@
+from typing import List, Optional
+from enum import Enum
+from google.adk.agents import LlmAgent
+from pydantic import BaseModel, Field
+
+class Priority(str, Enum):
+    LOW = "low"
+    MEDIUM = "medium" 
+    HIGH = "high"
+    CRITICAL = "critical"
+
+class SupportTicket(BaseModel):
+    title: str = Field(description="A concise summary of the issue")
+    description: str = Field(description="Detailed description of the problem")
+    priority: Priority = Field(description="The ticket priority level")
+    category: str = Field(description="The department this ticket belongs to")
+    steps_to_reproduce: Optional[List[str]] = Field(
+        description="Steps to reproduce the issue (for technical problems)",
+        default=None
+    )
+    estimated_resolution_time: str = Field(
+        description="Estimated time to resolve this issue"
+    )
+
+root_agent = LlmAgent(
+    name="customer_support_agent",
+    model="gemini-2.5-flash",
+    description="Creates structured support tickets from user reports",
+    instruction="""
+    You are a support ticket creation assistant.
+    
+    Based on user problem descriptions, create well-structured support tickets with appropriate priority levels, categories, and resolution estimates.
+    
+    IMPORTANT: Response must be valid JSON matching the SupportTicket schema with these fields:
+    - "title": Concise summary of the issue
+    - "description": Detailed problem description
+    - "priority": One of "low", "medium", "high", or "critical"
+    - "category": Department (e.g., "Technical", "Billing", "Account", "Product")
+    - "steps_to_reproduce": List of steps (for technical issues) or null
+    - "estimated_resolution_time": Estimated resolution time (e.g., "2-4 hours", "1-2 days")
+    
+    Format your response as valid JSON only.
+    """,
+    output_schema=SupportTicket,
+    output_key="support_ticket"
+) 

google_adk_tutorials/structured_output_agent/email_agent/README.md

@@ -1,4 +1,4 @@
-# 📧 Structured Output in Google ADK
+# 📧 Email Generation Agent with Structured Output
 
 A tutorial demonstrating how to implement structured output using Google's ADK (Agent Development Kit) framework. This example uses an email generator agent to show how to create type-safe, structured responses with Pydantic schemas and Gemini 2.5 Flash model.
 
@@ -25,7 +25,7 @@ A tutorial demonstrating how to implement structured output using Google's ADK (
    ```bash
    # Clone the repository
    git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
-   cd awesome-llm-apps/google_adk_tutorials/structured_output_agent/email_generator_agent
+   cd awesome-llm-apps/google_adk_tutorials/structured_output_agent/email_agent
 
    # Install dependencies
    pip install -r requirements.txt
@@ -38,7 +38,7 @@ A tutorial demonstrating how to implement structured output using Google's ADK (
 3. **Run the Agent**
    ```bash
    # Start the ADK web interface from the root folder
-   cd google_adk_tutorials/structured_output_agent
+   cd google_adk_tutorials/structured_output_agent/email_agent
    adk web
    ```
    Then:

google_adk_tutorials/structured_output_agent/email_agent/email_generator_agent/.env.example

@@ -0,0 +1,3 @@
+# If using Gemini via Google AI Studio
+GOOGLE_GENAI_USE_VERTEXAI=False
+GOOGLE_API_KEY="your-api-key"

google_adk_tutorials/structured_output_agent/email_agent/requirements.txt

@@ -0,0 +1,2 @@
+google-adk>=1.5.0
+pydantic>=2.0.0