القائمة
Bicep IaC templates to deploy Azure OpenAI, AI Search, and Application Insights. Reusable across any RAG project. Includes main.bicep and deploy.sh orchestration.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Scale up or scale down Azure RAG configurations (Search, Log Analytics, Insights) and manage budgets/alerts automatically. Reversible changes with cost calculation before applying.
PowerShell helper for obtaining Azure Blob Storage credentials via Azure CLI. Provides connection strings used by RAG indexers and document upload pipelines to access Blob Storage.
Design document ingestion and indexing workflows for Azure AI Search, including chunking, metadata strategy, and incremental reindexing guidance.
Exposes RAG functionality as a REST API for external applications. Provides HTTP endpoints for document search and query with JSON request/response, async processing, CORS support, and observability metrics.
Monitors, diagnoses and troubleshoots RAG system health. Verifies Azure AI Search connectivity, index status, configuration, and provides real-time monitoring with actionable error reports.
Professional executive report generation using Claude Opus 4.7. Generates high-quality DOCX reports with professional formatting, compelling narratives, and quantified impact metrics. Perfect for client presentations and stakeholder communication.
| name | rag-deployment-templates |
| description | Bicep IaC templates to deploy Azure OpenAI, AI Search, and Application Insights. Reusable across any RAG project. Includes main.bicep and deploy.sh orchestration. |
RAG Reference: Retrieval-augmented Generation (RAG) in Azure AI Search - Microsoft Learn
Status: Production
Version: 1.0
Assets incluidos: main.bicep, deploy.sh, deployer.py, indexer_runner.py, document_indexer.py
Plantillas Infrastructure-as-Code y orquestación de deployment para stack Azure completo:
# Mínima (Basic Search, 30d logs, LRS)
cd infra/
az deployment group create \
--resource-group rag-rg \
--template-file main.bicep \
--parameters searchTier=basic searchReplicaCount=1 searchPartitionCount=1 \
storageRedundancy=Standard_LRS logRetentionDays=30
# Estándar (Standard Search, 2 replicas, 90d logs)
az deployment group create \
--resource-group rag-rg \
--template-file main.bicep \
--parameters searchTier=standard searchReplicaCount=2 searchPartitionCount=1 \
storageRedundancy=Standard_LRS logRetentionDays=90
# Máxima (Standard Search, 3 replicas, 2 partitions, ZRS, 1 year logs)
az deployment group create \
--resource-group rag-rg \
--template-file main.bicep \
--parameters searchTier=standard searchReplicaCount=3 searchPartitionCount=2 \
storageRedundancy=Standard_ZRS logRetentionDays=365
Azure OpenAI Service (tier S0, pago por token)
gpt-4o-mini no se despliega (por debajo de barra de calidad para RAG)cost_analyzer.check_model_availability()Azure AI Search (Basic o Standard, configurable)
rag-documentsStorage Account (LRS o ZRS, configurable)
documentsApplication Insights + Log Analytics
Todos los precios son estimaciones en USD. Verify en https://azure.microsoft.com/en-us/pricing/calculator/
Mínima (Basic Search, 1 réplica, LRS, 30d logs):
Estándar (Standard Search, 2 réplicas, LRS, 90d logs):
Máxima (Standard Search, 3 réplicas + 2 particiones, ZRS, 365d logs):
Ver rag-cost-analyst/SKILL.md para desglose completo.
az group delete --name rag-rg --yes --no-wait