For the complete documentation index, see llms.txt. This page is also available as Markdown.

BI Genius Required Azure Services

Everything you need to deploy the BI Genius

BI Genius deploys two Azure services into your own Azure environment, alongside your existing Reporting Hub app.

BI Genius reuses your existing Reporting Hub Azure App Service; no additional App Service, SQL Database, capacity, or Translator is required.

Services BI Genius Deploys

Service
Purpose
Recommended starting point

Azure Database for PostgreSQL flexible server

Stores BI Genius configuration, agents, and query history.

Standard_B1ms tier, 32 GiB storage. Scale up later in the Azure portal.

Azure AI Foundry (Azure OpenAI)

Hosts the AI models that power BI Genius agents. Deployed to your own tenant, so your data and inference stay in your environment.

The three default models below. Add or change models any time.

AI Models and Token Costs

Because BI Genius runs on Azure AI Foundry in your own tenant, it does not restrict which AI models you can use. The installer deploys a working set of models by default, and you can deploy and select any other model available in Azure AI Foundry afterward.

Deployed by default:

Model
Used for

GPT (latest)

The primary chat/reasoning model behind agent answers.

GPT mini

A smaller, lower-cost model for lighter or faster requests.

text-embedding-3-small

Generates embeddings for semantic search and matching.

After installation, you can deploy additional models in Azure AI Foundry and choose which ones an agent uses from BI Genius AI Settings. See AI Settings to select models, and Token Limits in Azure to manage rate limits.

How token costs work

The models run in your own Azure subscription, so token usage is billed directly by Azure at Azure OpenAI pricing for whichever models you deploy. Reporting Hub does not add any token charge. Rates are pay-as-you-go and vary by model (input and output tokens are priced separately; embedding models are priced per token).

For current, per-model rates:

Because you own the Azure AI Foundry resource, you have full visibility and control over model choice and spend.

Key Points

The installer automatically configures both required resources. These services deploy to your own Azure environment rather than Reporting Hub's infrastructure, and all Azure subscription fees, including AI token usage, are the responsibility of your organization.

Your Reporting Hub app must be version 7.7.0 or higher to deploy BI Genius.

Last updated