azure-ai

Perform full-text search on text documents using Azure AI services.

6|2|Updated Jan 29, 2026

Search Tags:#ai #azure #search #speech #document intelligence

Ready to run

npx skills add https://github.com/jonathan-vella/azure-smb-rf --skill azure-ai-jonathan-vella

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: azure-ai
Source: https://github.com/jonathan-vella/azure-smb-rf/tree/main/.github/skills/azure-ai
Command: npx skills add https://github.com/jonathan-vella/azure-smb-rf --skill azure-ai-jonathan-vella

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires azure__search, azure__speech, az cognitiveservices, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a collection of AI services, including search, speech, and document intelligence, to solve complex problems like indexing and analyzing text, converting speech to text, and extracting information from documents.

Core Features & Use Cases

AI Search: Full-text, vector, and hybrid search capabilities.
Speech: Speech-to-text and text-to-speech functionality.
OpenAI: Access to GPT models, embeddings, and DALL-E.
Document Intelligence: Form extraction and OCR.
Use Case: Use this Skill to build applications that require advanced text analysis, speech recognition, or document processing.

Quick Start

Use the azure-ai skill to perform a full-text search on the provided text document 'sample.txt'.

Frequently Asked Questions about azure-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I perform vector search and full-text search on text documents?▼

Full-text and vector search are executed by indexing text documents within a configured search service, enabling hybrid queries that combine keyword matching and vector similarity to retrieve relevant information.

Can I extract text from images and forms using OCR and document intelligence?▼

Yes, you can extract text from images and forms using document intelligence capabilities. This functionality performs form extraction and optical character recognition to pull structured information from scanned documents.

Do I need Azure Cognitive Services configured to use speech-to-text and text-to-speech?▼

Yes, Azure Cognitive Services must be properly configured to use speech-to-text and text-to-speech. The suite requires Azure Search, Azure Speech, and Azure AI services to be available in your environment.

What is the best way to convert speech to text and generate spoken audio?▼

The best way to convert speech to text and generate spoken audio is by using a configured speech service. This provides dedicated speech-to-text recognition for transcription and text-to-speech synthesis for audio generation.

Does this approach work with GPT models and embeddings for text analysis?▼

Yes, this approach works with GPT models and embeddings for text analysis. It provides access to OpenAI capabilities, allowing you to generate text, create vector embeddings, and produce images with DALL-E.

When should I not use a single suite for search, speech, and document intelligence?▼

You should not use a single suite for search, speech, and document intelligence if your environment lacks the required Azure dependencies. It requires Azure Search, Azure Speech, and Azure AI services to be available and properly configured.