Search

More Filters

Show More
Add Listing
Go Back

azure-ai-travel-agents

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

This repository is an enterprise-grade sample application that demonstrates how to build and run a multi-agent travel assistant using LlamaIndex.TS and the Model Context Protocol (MCP). It provides a deployable reference architecture showing multiple specialized agents for travel workflows such as customer query understanding, destination recommendation, itinerary planning, code evaluation, model inference and web search. MCP servers implemented in Python, Node.js, Java and .NET expose tool capabilities to agents. All components are containerized with Docker and designed to run serverlessly on Azure Container Apps or locally via Docker Model Runner. The project includes orchestration services, monitoring via an Aspire Dashboard with OpenTelemetry integration, an llms.txt file to aid LLM inference, a one-step preview setup script for local testing, advanced setup documentation, deployment instructions using azd up, and cleanup guidance for Azure resources.

Links

Stars
294
Language
App URL
https://github.com/Azure-Samples/azure-ai-travel-agents
Github Repository
https://github.com/Azure-Samples/azure-ai-travel-agents/blob/main/README.md

Categorization

App Details

Features
Multiple specialized AI agents orchestrated by LlamaIndex.TS to handle distinct travel tasks such as preference extraction, recommendations and itinerary generation. MCP integration with example servers implemented in Python, Node.js, Java and .NET so agents can call external tools and services. Containerized deployment using Docker and guidance for Azure Container Apps serverless hosting. Support for high-performance model inference using ONNX and vLLM on serverless GPU instances. Local preview via Docker Model Runner and a one-step setup script to bootstrap the repository, download models, build images and configure environment files. Observability with Aspire Dashboard and OpenTelemetry. Includes llms.txt to provide model-time metadata, cost estimation guidance, quick deploy scripts using azd and an advanced setup and troubleshooting guide.
Use Cases
This sample helps developers and architects learn how to design, orchestrate and deploy multi-agent systems for travel scenarios using modern LLM tooling and MCP. It provides working examples of agent workflows, multi-language MCP servers, containerized tooling and end-to-end deployment patterns to Azure Container Apps, enabling reproducible demos of recommendation, planning and search capabilities. The local preview option lets teams test agents and large models without immediate cloud costs while guidance on Azure deployment and cost estimation helps plan production rollouts. Observability and monitoring examples demonstrate how to track agent behavior. The repo is useful as a reference implementation for integrating LLMs, custom inference, tool invocation and service orchestration in enterprise agent applications.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)
listing image

Curie

0 (0 review)

Featured Listings

Tags

Please fill the required fields*