Skip to content

Commit ec937ee

Browse files
committed
quest 5
1 parent 286d698 commit ec937ee

File tree

6 files changed

+96
-211
lines changed

6 files changed

+96
-211
lines changed
Lines changed: 96 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,96 @@
1+
![Burger Ordering Agent Logo](./assets/burger-logo.png)
2+
3+
Livestream starting soon! **Click below to register.**
4+
5+
[![Reactor Livestream](./assets/poster-quest5.png)](https://developer.microsoft.com/en-us/reactor/events/26786/)
6+
7+
## Overview
8+
9+
In this quest, you will set up and run a **complete end-to-end Burger Ordering Agent system** using LangChain.js. Once you have completed the setup, you will start a CodeTour that will guide you through each step of the Agentic solution design and implementation with detailed explanations.
10+
11+
![Serverless RAG - CodeTour](./assets/burger-system.png)
12+
13+
> [!NOTE]
14+
>
15+
> **Hackathon Award Category: Agentic System Architecture Award**
16+
>
17+
> As part of the Build-a-thon Hack!, we have a special award category recognizing agentic designs that are **useful, reliable, and secure**.
18+
>
19+
> This quest demonstrates foundational patterns: **MCP tool integration** enables agents to interact with external systems (useful), **structured agent workflows** with proper error handling ensure consistent behavior (reliable), and **API-based architectures** allow for controlled access and validation (secure).
20+
>
21+
> Consider how these patterns can help you build production-ready agent systems that users can trust.
22+
23+
## Steps to Complete the Quest
24+
25+
### Codebase Setup
26+
27+
1. **Fork and Clone the Repository**: Start by [forking](https://github.com/Azure-Samples/mcp-agent-langchainjs/fork) the AI Agent with MCP tools using LangChain.js repository to your GitHub account and then clone it.
28+
29+
```bash
30+
git clone https://github.com/<your-username>/mcp-agent-langchainjs.git
31+
```
32+
33+
Navigate to the project directory:
34+
35+
```bash
36+
cd mcp-agent-langchainjs
37+
```
38+
39+
2. **Install Dependencies**: Install the required project dependencies using:
40+
41+
```bash
42+
npm install
43+
```
44+
45+
3. **Start the Application**:
46+
47+
Launch the application with:
48+
49+
```bash
50+
npm start
51+
```
52+
53+
> [!NOTE]
54+
> Starting the different services may take some time, you need to wait until you see the following message in the terminal: **🚀 All services ready 🚀**
55+
>
56+
> This will start:
57+
>
58+
> - Agent Web App: http://localhost:4280
59+
> - Agent API: http://localhost:7072
60+
> - Burger Web App: http://localhost:5173
61+
> - Burger API: http://localhost:7071
62+
> - Burger MCP Server: http://localhost:3000
63+
64+
### Start the CodeTour
65+
66+
This quest is designed to give you a guided tour of the codebase and its implementation of the complete Agentic solution. Follow these steps to start the CodeTour:
67+
68+
1. **Install the CodeTour Extension**: If you haven't already, install the [CodeTour extension](https://marketplace.visualstudio.com/items?itemName=vsls-contrib.codetour) in Visual Studio Code.
69+
70+
2. **Open the CodeTour**: Open the Command Palette (Ctrl+Shift+P or Cmd+Shift+P on Mac) and type "**CodeTour: Start Tour**".
71+
72+
![Start CodeTour](./assets/agent-codetour.png)
73+
74+
There are 6 tours to walk you through the entire agent implementation flow. We recommend going through them in order as they build upon each other.
75+
76+
- Tour 1: Introduction: Understanding AI Agents (7 steps)
77+
- Tour 2: Designing AI Agents (8 steps)
78+
- Tour 3: Building MCP Tools (10 steps)
79+
- Tour 4: Building the Agent API (7 steps)
80+
- Tour 5: Backend API Design (7 steps)
81+
- Tour 6: Scaling with Azure Infrastructure (4 steps)
82+
83+
> [!WARNING]
84+
> Trouble viewing the CodeTour? Try setting `comments.maxHeightExceeded` to `false`
85+
86+
### Return to the Build-a-thon
87+
88+
Once you have completed the CodeTour and explored the Agent implementation, return to the main Build-a-thon repository to continue with the next step.
89+
90+
## Stay connected
91+
92+
Have a question, project or insight to share? Post in the [Agentic Systems discussion hub](https://github.com/Azure-Samples/JavaScript-AI-Buildathon/discussions/91)
93+
94+
## AI Note
95+
96+
This quest was partially created with the help of AI. The author reviewed and revised the content to ensure accuracy and quality.
355 KB
Loading
8.34 KB
Loading
831 KB
Loading
1.58 MB
Loading

05-explore-frameworks/README.md

Lines changed: 0 additions & 211 deletions
This file was deleted.

0 commit comments

Comments
 (0)