Aller au contenu
TakoAPI
Retour aux skills

azure-ai-projects-py

par thegovind

DevOps & Cloud
1.7kTéléchargements rapportés par clawskills.sh
1Étoiles
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Build AI applications using the Azure AI Projects.

Description

Ce que fait ce skill

Python SDK for building AI applications on Azure AI Foundry. Manages agents, threads, evaluations, connections, deployments, datasets, and indexes through a single project client. Supports both native Foundry operations and an OpenAI-compatible client interface.

Provides unified access to agents, evaluations, connections, and deployments through a single Foundry-aware client rather than managing multiple Azure SDK clients separately.

Quand l'utiliser

  • Building versioned customer support agents for production deployments
  • Running fluency and task-adherence evaluations on agent outputs
  • Searching Azure AI indexes from within an agent workflow
  • Listing and selecting model deployments across a Foundry project
  • Creating code-executing agents that run Python on user requests

Exemple de workflow

ENTRÉE

User asks: 'Set up an agent that can execute code and answer questions'

AGENT
  1. 1

    Authenticate with DefaultAzureCredential and initialize AIProjectClient

  2. 2

    Create an agent with CodeInterpreterTool and custom instructions

  3. 3

    Open a thread and post the user message

  4. 4

    Call create_and_process to run the agent on the thread

  5. 5

    Read assistant messages from the completed run

SORTIE

Agent response with executed code results returned from the thread messages

Prérequis

  • AZURE_AI_PROJECT_ENDPOINT environment variable
  • AZURE_AI_MODEL_DEPLOYMENT_NAME environment variable
  • Azure account with an AI Foundry project

Installation

clawhub install thegovind/azure-ai-projects-py

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens