Azure-Samples/azure-search-power-skills

A collection of useful functions to be deployed as custom skills for Azure Cognitive Search

What it solves

This repository provides sample implementations for custom enrichment skills in Azure AI Search. It addresses the gap when built-in enrichment skills are insufficient for a user's specific needs, such as requiring custom business logic, integration with external proprietary systems, or specific data transformations during the indexing pipeline.

How it works

The project provides a collection of reusable patterns and code samples in C# and Python to build and host "Custom Web API skills." These skills act as external endpoints that Azure AI Search calls during its indexing process to enrich data. Users can adapt these samples to their own data contracts and host them (often using Azure Functions) to integrate them into their search indexer's skillset.

Who it’s for

Developers building search indexes in Azure AI Search who need to extend the indexing pipeline with custom logic or external API calls that are not provided by the built-in cognitive skills.

Highlights

  • Diverse Skill Samples: Includes implementations for chat completion (using Azure OpenAI), geolocation (GeoPointFromName), and video insight extraction (VideoIndexer).
  • Multi-language Support: Provides templates and samples in both C# and Python (FastAPI).
  • Ready-to-Deploy: Many samples include "Deploy to Azure" buttons for rapid prototyping.
  • Extensible Templates: Offers "Hello World" and FastAPI scaffolds to help developers start their own custom skills from scratch.

Related

  • Project
    Azure-Samples/openai

    A collection of practical code samples and templates for building agentic workflows and AI solutions using Azure AI Foundry and Azure OpenAI Service.

  • Project
    microsoft/skills

    Microsoft / skills is a genuine open‑source toolbox that equips AI coding agents (e.g., GitHub Copilot) with ready‑made, Azure‑specific “skills” – code snippets, templates, and MCP server scaffolding – so the agents can generate correct Azure SDK calls, manage Foundry resources, and follow governance patterns. Install via `npx skills add microsoft/skills`, pick only the needed skills (≈175 across Python, .NET, TypeScript, Java, Rust), and use the provided `AGENTS.md` and MCP configs to build custom agents for backend, frontend, infrastructure, or planning tasks.

  • Project
    MicrosoftDocs/Agent-Skills

    A curated collection of agentic skills based on an open standard that provides AI coding assistants with expert-level, production-ready knowledge of Azure services.

  • Project
    owndev/Open-WebUI-Functions

    A collection of Python-based pipelines and filters that extend Open WebUI with integrations for Azure AI, Google Gemini, N8N automation, and performance monitoring tools.

  • Project
    Azure-Samples/cognitive-services-speech-sdk

    A collection of cross-platform code samples demonstrating how to use the Microsoft Cognitive Services Speech SDK for speech recognition, synthesis, and translation.