🧪

Created By
Azure-Samplesa year ago
APIM ❤️ AI - This repo contains experiments on Azure API Management's AI capabilities, integrating with Azure OpenAI, AI Foundry, and much more 🚀
Overview

What is AI-Gateway?

AI-Gateway is a project that explores the integration of Azure API Management with AI capabilities, including Azure OpenAI and AI Foundry, through a series of experimental labs.

How to use AI-Gateway?

To use AI-Gateway, clone the repository, set up the required prerequisites, and navigate through the available labs to experiment with various AI functionalities.

Key features of AI-Gateway?

  • Experiments with Model Context Protocol (MCP) for client authorization.
  • Integration with Azure OpenAI models and APIs.
  • Tools for managing AI budgets and costs through the FinOps Framework.
  • Various labs for testing AI functionalities like content filtering, prompt shielding, and model routing.

Use cases of AI-Gateway?

  1. Experimenting with AI models and APIs in a controlled environment.
  2. Managing AI service costs effectively.
  3. Implementing advanced AI functionalities in applications.

FAQ from AI-Gateway?

  • What prerequisites are needed to use AI-Gateway?

You need Python 3.12 or later, VS Code with Jupyter extension, an Azure subscription, and Azure CLI installed.

  • Is AI-Gateway suitable for production use?

AI-Gateway is primarily for experimentation and learning; production use should follow best practices from the Azure Well-Architected Framework.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Azure-Samples
Star
629
Language
Jupyter Notebook
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago