microsoft/foundrysamples

microsoft/foundrysamples

Description: This repository contains easy-to-use sample code snippets and implementation examples for common development scenarios. The content is intended for educational, learning, and demonstration purposes only.

Language: Python

License: MIT

Stars: 0

Forks: 0

Open issues: 2

Created: 2026-07-15T16:04:33Z

Pushed: 2026-07-20T06:41:45Z

Default branch: main

Fork: no

Archived: no

README: --- title: Microsoft AI Python Samples description: Roadmap for Python samples that add Microsoft AI capabilities to existing applications ms.date: 2026-07-15 ms.topic: overview keywords:

• Microsoft Foundry
• Python
• generative AI
• reference samples

---

Purpose

This repository will provide small, runnable Python references for developers who want to add Microsoft AI capabilities to an existing application. The collection will progress from a single model call to retrieval, agents, evaluation, and production operations without requiring developers to adopt a complete starter application.

The first release will contain 24 snippets across six modules and one capstone application. Each snippet will teach one integration pattern and take about 10 to 20 minutes to understand and run.

Audience and scope

The samples target Python developers who can run a virtual environment and know basic HTTP and asynchronous programming. They may be adding AI to a web API, worker, command-line tool, or existing business application.

The series will use current Microsoft-supported libraries where each one owns the problem:

• The OpenAI Python client for direct model inference through Microsoft Foundry
• azure-identity for local and managed identity authentication
• azure-ai-projects for Foundry project operations
• Microsoft Agent Framework for agent and workflow patterns
• azure-search-documents for production retrieval
• azure-ai-evaluation for quality measurement
• OpenTelemetry and Azure Monitor for tracing and operations

SDK versions and model names will be pinned in each module. Shared helpers will be limited to authentication and configuration so readers can copy a snippet into an existing project without importing this repository.

Sample catalog

Module 1: Connect to a model

1. [Send a minimal text request using Microsoft Entra ID](01-model-basics/01-minimal-text-request/) 2. [Stream a response and handle cancellation](01-model-basics/02-streaming-response/) 3. [Return validated structured output as a Python model](01-model-basics/03-structured-output/) 4. [Send text and an image in a multimodal request](01-model-basics/04-multimodal-request/)

Outcome: developers can make secure model calls and choose between text, streaming, structured, and multimodal responses.

Module 2: Integrate with an application

5. [Wrap model access behind an application service](02-application-integration/01-model-service/) 6. [Add an AI endpoint to an existing FastAPI application](02-application-integration/02-fastapi-endpoint/) 7. [Handle timeouts, throttling, retries, and service errors](02-application-integration/03-resilience-and-errors/) 8. [Test AI-dependent code with a fake client and deterministic fixtures](02-application-integration/04-testing-with-fakes/)

Outcome: developers can add AI without coupling business logic to an SDK or a specific model deployment.

Module 3: Ground responses with data

9. [Create embeddings for local documents](03-grounding-and-search/01-document-embeddings/) 10. [Build and query a small local vector index](03-grounding-and-search/02-local-vector-index/) 11. [Retrieve from Azure AI Search with filters](03-grounding-and-search/03-azure-ai-search/) 12. [Generate a grounded answer with citations and a no-answer path](03-grounding-and-search/04-grounded-answers-with-citations/)

Outcome: developers can build a retrieval-augmented generation flow, understand its moving parts, and avoid unsupported answers.

Module 4: Add tools and agents

13. [Define and execute a typed function tool](04-tools-and-agents/01-typed-function-tool/) 14. [Run a multi-turn agent with conversation state](04-tools-and-agents/02-multi-turn-agent/) 15. [Require human approval before a sensitive tool call](04-tools-and-agents/03-human-approval/) 16. [Coordinate a small sequential workflow with Microsoft Agent Framework](04-tools-and-agents/04-sequential-workflow/)

Outcome: developers can decide when function calling is enough and when an agent or workflow is justified.

Module 5: Improve safety and quality

17. [Apply input and output content safety checks](05-safety-and-evaluation/01-content-safety/) 18. [Defend a grounded flow against prompt injection and unsafe tool arguments](05-safety-and-evaluation/02-prompt-injection-defense/) 19. [Build a versioned JSON Lines evaluation dataset](05-safety-and-evaluation/03-evaluation-dataset/) 20. [Run relevance, groundedness, safety, and task-success evaluations](05-safety-and-evaluation/04-quality-evaluation/)

Outcome: developers can define measurable quality gates before releasing an AI feature.

Module 6: Prepare for production

21. [Trace model, retrieval, and tool calls with OpenTelemetry](06-production-readiness/01-opentelemetry-tracing/) 22. [Record latency, token usage, errors, and estimated cost without logging secrets](06-production-readiness/02-metrics-and-cost/) 23. [Use DefaultAzureCredential locally and managed identity in Azure](06-production-readiness/03-managed-identity/) 24. [Add concurrency limits, fallback behavior, and graceful degradation](06-production-readiness/04-concurrency-and-fallbacks/)

Outcome: developers can observe, secure, and operate an AI feature in an existing service.

Capstone application

The capstone will be a support-answer API added to a small existing FastAPI service. It will reuse the patterns from the snippets to provide retrieval with citations, a read-only ticket lookup tool, structured responses, safety checks, evaluation, and tracing.

The capstone is an integration example, not a new framework. Its code will link back to the relevant snippets so developers can adopt only the pieces they need.

Repository layout

foundrysamples/
|-- 01-model-basics/
|-- 02-application-integration/
|-- 03-grounding-and-search/
|-- 04-tools-and-agents/
|-- 05-safety-and-evaluation/
|-- 06-production-readiness/
|-- capstone-support-api/
|-- shared/
|-- .env.example
|-- pyproject.toml
`-- README.MD

Each numbered snippet folder will...